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

    Neuronpedia

    INDEX
    Explanations

    actions or processes that indicate a sequence of steps or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bid
    -0.61
    jured
    -0.60
    nai
    -0.60
    voy
    -0.59
    bold
    -0.59
    existent
    -0.58
    acus
    -0.58
     Himself
    -0.57
     resisted
    -0.57
     Bac
    -0.56
    POSITIVE LOGITS
    abeth
    0.89
     proceed
    0.85
    NetMessage
    0.80
     then
    0.78
    =-=-=-=-=-=-=-=-
    0.77
     rinse
    0.77
     commence
    0.75
     THEN
    0.74
     resumes
    0.74
     begin
    0.73
    Act Density 0.131%

    No Known Activations