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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making or action

    oai_token-act-pair · gpt-3.5-turbo

    frequent verbs indicating decisions or actions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assic
    -0.79
    Avg
    -0.69
    atto
    -0.68
    pmwiki
    -0.68
    angular
    -0.67
    nutrition
    -0.66
    fortunately
    -0.65
    stellar
    -0.65
    İ
    -0.64
    icult
    -0.64
    POSITIVE LOGITS
    enance
    0.92
    dress
    0.75
     him
    0.75
     them
    0.72
     HIS
    0.69
    igate
    0.67
     oneself
    0.67
     anything
    0.64
     THEM
    0.64
     seiz
    0.62
    Act Density 0.292%

    No Known Activations