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

    Neuronpedia

    INDEX
    Explanations

    expressions related to self-deception and blame

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ForValue
    -0.55
    SizeF
    -0.54
     Roskov
    -0.50
    nsics
    -0.50
    чан
    -0.49
     Freezing
    -0.49
     ecc
    -0.49
    freezing
    -0.49
    grin
    -0.49
     misto
    -0.48
    POSITIVE LOGITS
    Numerology
    0.67
    IsContent
    0.66
    __":
    0.66
    __':
    0.64
     MainAxisSize
    0.64
     desperate
    0.60
    complexContent
    0.60
     AssemblyTitle
    0.60
     Riproduzione
    0.56
    出版年
    0.54
    Act Density 0.192%

    No Known Activations