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

    Neuronpedia

    INDEX
    Explanations

    computer code snippets containing function names

    oai_token-act-pair · gpt-3.5-turbo

    patterns or structures related to coding and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysis
    -0.67
    uyomi
    -0.66
     GOODMAN
    -0.65
    hess
    -0.63
    hap
    -0.63
    hun
    -0.62
    google
    -0.62
    agra
    -0.61
    tackle
    -0.60
     Hua
    -0.60
    POSITIVE LOGITS
    (
    1.03
    (_
    0.99
     (_
    0.97
     (
    0.96
    (&
    0.92
    (*
    0.89
    (\
    0.88
    (-
    0.87
    ('
    0.84
     (%
    0.84
    Act Density 0.099%

    No Known Activations