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

    Neuronpedia

    INDEX
    Explanations

    names with a title (like Mr. or Mrs.)

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    20439
    -0.76
     favour
    -0.64
     pione
    -0.64
     organising
    -0.62
    sbm
    -0.60
     actionGroup
    -0.60
     front
    -0.60
     fibre
    -0.59
     Stuff
    -0.54
     analyse
    -0.54
    POSITIVE LOGITS
    .,
    1.34
    .;
    1.23
    .?
    1.20
    .,"
    1.15
    ./
    1.14
    .-
    1.02
    .—
    0.99
    .),
    0.95
    .:
    0.94
    .--
    0.89
    Act Density 0.137%

    No Known Activations