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

    Neuronpedia

    INDEX
    Explanations

    positive superlatives indicating excellence

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives indicating high quality or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appings
    -0.80
    é¾į
    -0.78
    ymes
    -0.77
    ourning
    -0.76
    rahim
    -0.73
    adders
    -0.70
    asions
    -0.70
    èĪ
    -0.68
    ancies
    -0.68
    iencies
    -0.68
    POSITIVE LOGITS
     thing
    1.18
     predictor
    0.97
     ever
    0.96
     conceivable
    0.93
     imaginable
    0.92
     EVER
    0.85
     example
    0.83
     piece
    0.81
     sounding
    0.81
     indicator
    0.81
    Act Density 0.164%

    No Known Activations