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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 779
    Prev
    Next
    INDEX
    Explanations

    the phrase "likes of" followed by various names or characters

    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
    isting
    -0.70
     undertake
    -0.68
    WER
    -0.68
     necess
    -0.62
     entails
    -0.61
    will
    -0.61
     anyone
    -0.60
    wp
    -0.60
    OK
    -0.60
    verages
    -0.60
    POSITIVE LOGITS
    ragon
    0.76
     Cosponsors
    0.73
     Chains
    0.72
    ial
    0.71
    antry
    0.71
    inas
    0.70
     Binding
    0.68
     Trafford
    0.67
    ordon
    0.65
     Cutter
    0.65
    Activations Density 0.048%

    No Known Activations