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

    Neuronpedia

    INDEX
    Explanations

    dates in the month and year format

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ching
    -1.08
    fman
    -1.06
    istics
    -1.05
    emort
    -1.04
    kus
    -1.04
    king
    -1.02
    cci
    -1.00
    itton
    -0.99
    zai
    -0.96
    vet
    -0.95
    POSITIVE LOGITS
     Surprise
    1.41
    opus
    1.12
    avia
    1.06
    nard
    0.98
    acious
    0.98
    hens
    0.97
    å¹
    0.96
    boro
    0.94
    OB
    0.94
     Fool
    0.93
    Act Density 0.705%

    No Known Activations