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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations or identifiers associated with variables and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OFF
    -0.88
     GOODMAN
    -0.79
     COM
    -0.78
     MAY
    -0.74
     FOX
    -0.69
     MUST
    -0.68
     COVER
    -0.68
     SHOULD
    -0.67
     IPS
    -0.66
     RAW
    -0.65
    POSITIVE LOGITS
    b
    1.47
    n
    1.45
    d
    1.43
    h
    1.41
    f
    1.40
    s
    1.39
    p
    1.37
    l
    1.34
    r
    1.34
    t
    1.34
    Act Density 0.253%

    No Known Activations