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 values and specific identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.82
     Frankfurt
    -0.77
     Feder
    -0.76
     PASS
    -0.76
     Confeder
    -0.74
     Patron
    -0.68
     Farmer
    -0.67
     contractual
    -0.66
     lobbying
    -0.66
     CRA
    -0.66
    POSITIVE LOGITS
    x
    1.65
    xs
    1.36
    xes
    1.33
    xb
    1.24
    xff
    1.23
    X
    1.23
    xd
    1.20
    xc
    1.19
    xa
    1.18
     x
    1.18
    Act Density 0.107%

    No Known Activations