© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 697
    Prev
    Next
    INDEX
    Explanations

    descriptions of chaotic or problematic situations

    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
    }:
    -0.57
    chieve
    -0.54
    zzy
    -0.53
    atre
    -0.49
    ef
    -0.49
    affe
    -0.49
     )]
    -0.49
    pheus
    -0.48
    ten
    -0.47
    latest
    -0.47
    POSITIVE LOGITS
    that
    1.42
     that
    1.40
     THAT
    1.19
     That
    0.98
    That
    0.97
     thats
    0.86
    ikers
    0.69
    bye
    0.64
    ito
    0.62
    ジ
    0.61
    Activations Density 2.197%

    No Known Activations