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

    Neuronpedia

    INDEX
    Explanations

    superlatives indicating the highest degree or ranking

    oai_token-act-pair · gpt-3.5-turbo

    superlative claims or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rapnel
    -0.70
    insk
    -0.70
    oult
    -0.69
    oute
    -0.68
    ensing
    -0.67
    lav
    -0.66
    itu
    -0.65
    ice
    -0.65
    rar
    -0.65
    ricted
    -0.64
    POSITIVE LOGITS
     recorded
    1.02
     conceived
    0.95
     seen
    0.92
     produced
    0.91
     dreamed
    0.90
     achieved
    0.86
     bestowed
    0.85
     imagined
    0.85
     assembled
    0.84
     attained
    0.83
    Act Density 0.017%

    No Known Activations