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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the superlative form (e.g. "greatest", "best") or ranking in terms of quality

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ERAL
    -0.77
    ulton
    -0.69
    avascript
    -0.69
    icio
    -0.69
    aspx
    -0.66
     Bullets
    -0.65
    oren
    -0.65
    ose
    -0.63
    ento
    -0.63
    rar
    -0.63
    POSITIVE LOGITS
     recorded
    1.20
     conceived
    1.15
     devised
    1.12
     produced
    0.99
     seen
    0.97
     assembled
    0.97
     imagined
    0.96
     achieved
    0.95
     bestowed
    0.92
     dreamed
    0.91
    Act Density 0.034%

    No Known Activations