Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific verbs related to actions being performed on objects

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding quantities or conditions involving objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reading
    -0.71
    rawdownloadcloneembedreportprint
    -0.70
    advertisement
    -0.70
    ="#
    -0.67
    Honest
    -0.65
     Investigative
    -0.64
    Dispatch
    -0.63
    Know
    -0.62
    Truth
    -0.62
    Opening
    -0.60
    POSITIVE LOGITS
     dominated
    1.04
     preferred
    0.95
     preferable
    0.94
     dominate
    0.90
     predomin
    0.88
     favored
    0.86
     typically
    0.86
     favoured
    0.86
     mostly
    0.83
     narrower
    0.83
    Act Density 0.598%

    No Known Activations