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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of a subject's actions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogether
    -0.58
    Trend
    -0.57
    Basic
    -0.56
    sylv
    -0.54
    *.
    -0.53
    environment
    -0.53
    collect
    -0.53
    results
    -0.53
    common
    -0.53
    process
    -0.52
    POSITIVE LOGITS
     resign
    0.84
     accuser
    0.83
     resigned
    0.81
     sacked
    0.79
    zbollah
    0.78
     apologised
    0.77
     arra
    0.77
     resignation
    0.77
     himself
    0.77
     acquitted
    0.76
    Act Density 0.674%

    No Known Activations