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

    Neuronpedia

    INDEX
    Explanations

    the word "supposed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.60
    ที่
    -0.55
    ьаж
    -0.51
     dica
    -0.51
     Poehler
    -0.51
     Eritrea
    -0.50
    Sting
    -0.49
     Inquiry
    -0.48
    ENTIALS
    -0.48
     ventilated
    -0.48
    POSITIVE LOGITS
     suppose
    1.95
     supposed
    1.76
    supposed
    1.71
     supposes
    1.30
     suppos
    1.18
     Sup
    1.06
    Suppose
    1.05
     Suppose
    1.05
    sup
    1.02
    Sup
    1.02
    Act Density 0.073%

    No Known Activations