© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1026
    Prev
    Next
    INDEX
    Explanations

    mentions of the news outlet CNN

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     folds
    -0.80
     Beir
    -0.77
    arks
    -0.70
     eleph
    -0.68
     tatt
    -0.66
     rou
    -0.65
     teasp
    -0.64
     Parish
    -0.64
     disg
    -0.63
     Rober
    -0.61
    POSITIVE LOGITS
    oS
    0.79
    bernatorial
    0.77
    opathic
    0.75
    usterity
    0.74
    political
    0.72
    opathy
    0.70
     constitu
    0.70
    galitarian
    0.69
    ATURE
    0.68
    vre
    0.67
    Activations Density 0.008%

    No Known Activations