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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences describing situations or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "what happens" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    severe
    -0.74
    ondo
    -0.72
    shaw
    -0.72
    stra
    -0.71
    chet
    -0.69
    ilts
    -0.68
    rum
    -0.68
    serv
    -0.67
    rollers
    -0.67
    ikk
    -0.67
    POSITIVE LOGITS
    uate
    0.78
    ometimes
    0.77
     Ambro
    0.75
    uating
    0.74
    Ñĭ
    0.70
    uates
    0.70
    aea
    0.69
     =================================
    0.68
    rences
    0.66
     unavoid
    0.65
    Act Density 0.030%

    No Known Activations