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

    Neuronpedia

    INDEX
    Explanations

    names or references to specific individuals named Jack

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.74
    cation
    -0.71
     laureate
    -0.70
    ndra
    -0.69
     revolving
    -0.68
    iferation
    -0.67
    IFIED
    -0.66
    EMBER
    -0.66
     describ
    -0.66
     sugg
    -0.66
    POSITIVE LOGITS
     Sparrow
    1.11
    intosh
    1.02
     Daniels
    0.94
     Straw
    0.94
    knife
    0.90
    pots
    0.89
     Nicholson
    0.84
    hammer
    0.82
    OTA
    0.80
    assi
    0.80
    Act Density 11.370%

    No Known Activations