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

    Neuronpedia

    INDEX
    Explanations

    terms related to health and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "can" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fighter
    -0.68
     Quarter
    -0.63
     honoring
    -0.63
     striving
    -0.62
     competitor
    -0.62
     Fighting
    -0.62
     BAL
    -0.61
     Seeking
    -0.61
     Moz
    -0.60
     Mant
    -0.59
    POSITIVE LOGITS
    't
    1.57
    berra
    1.23
    adian
    1.22
    isters
    1.11
    NOT
    1.04
    ister
    1.04
     afford
    0.94
     easily
    0.92
    vas
    0.91
     attest
    0.90
    Act Density 0.174%

    No Known Activations