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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.82
    ,
    -0.78
     -
    -0.75
     in
    -0.75
    ub
    -0.75
    od
    -0.69
     
    -0.69
    -
    -0.68
     du
    -0.68
     a
    -0.67
    POSITIVE LOGITS
     myſelf
    1.91
     purpoſe
    1.82
     Jefus
    1.75
     itſelf
    1.71
     Efq
    1.68
     Majefty
    1.67
     pleaſure
    1.66
     Theſe
    1.61
     Anſ
    1.61
     raiſ
    1.60
    Act Density 0.070%

    No Known Activations