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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.75
     виправивши
    -0.59
    FormTagHelper
    -0.58
    ]^{-
    -0.55
     prä
    -0.55
    oprot
    -0.55
    нрави
    -0.53
    }=\{
    -0.51
     userSchema
    -0.50
    (":");
    -0.50
    POSITIVE LOGITS
     know
    0.79
    我知道
    0.76
    Certainly
    0.76
     certainly
    0.73
     wiem
    0.71
     understand
    0.69
     knows
    0.69
     Certainly
    0.65
     connais
    0.64
     certeza
    0.63
    Act Density 0.111%

    No Known Activations