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

    Neuronpedia

    INDEX
    Explanations

    the word "can" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.88
    tieth
    -0.81
    Lähteet
    -0.80
    PerformLayout
    -0.80
    unknownFields
    -0.78
     pageContext
    -0.78
     Affiliations
    -0.77
     nisi
    -0.73
     azzurro
    -0.73
    -------
    -0.71
    POSITIVE LOGITS
     can
    2.10
     Can
    1.71
     CAN
    1.70
    Can
    1.60
    can
    1.60
     could
    1.31
    ocan
    1.29
     può
    1.27
    CAN
    1.22
     may
    1.22
    Act Density 0.245%

    No Known Activations