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

    Neuronpedia

    INDEX
    Explanations

    references to broader or wider concepts, contexts, or communities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    girls
    -0.70
    _-
    -0.68
    Lex
    -0.67
    boy
    -0.67
    liest
    -0.65
    visor
    -0.65
    girl
    -0.64
    Guard
    -0.64
     Drawn
    -0.64
    rol
    -0.63
    POSITIVE LOGITS
     societal
    0.94
     spectrum
    0.85
    soType
    0.83
     than
    0.79
     reperto
    0.79
     context
    0.78
     ado
    0.77
     organis
    0.74
     circulation
    0.73
     ensemble
    0.71
    Act Density 5.177%

    No Known Activations