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

    Neuronpedia

    INDEX
    Explanations

    assertions and confidence in beliefs or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.67
     CommandType
    -0.54
    styleUrls
    -0.52
    hesus
    -0.51
    enido
    -0.51
    arraycopy
    -0.51
    angliski
    -0.49
    Enders
    -0.49
     mía
    -0.48
    IVersion
    -0.47
    POSITIVE LOGITS
    Surely
    1.03
     surely
    1.00
     Surely
    0.95
     must
    0.68
     Must
    0.65
    Must
    0.63
    følgelig
    0.63
    няка
    0.61
    sure
    0.60
    无疑
    0.59
    Act Density 0.280%

    No Known Activations