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

    Neuronpedia

    INDEX
    Explanations

    instances of the verbs "is" and "was"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consequ
    -0.74
    CloseOperation
    -0.72
     BoxDecoration
    -0.69
     Pfalz
    -0.68
    AddTagHelper
    -0.67
     perio
    -0.66
    igenschaften
    -0.66
    RefNanny
    -0.66
    голь
    -0.65
    ThroughAttribute
    -0.65
    POSITIVE LOGITS
     Is
    1.15
    Is
    1.10
     IS
    0.94
     Ishi
    0.93
     Ist
    0.81
    Was
    0.81
     is
    0.81
    is
    0.80
    isPrime
    0.80
     dieux
    0.79
    Act Density 0.285%

    No Known Activations