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

    Neuronpedia

    INDEX
    Explanations

    numbers in a specific range

    oai_token-act-pair · gpt-3.5-turbo

    numerical data associated with statistics or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.73
    ulet
    -0.71
    sole
    -0.67
    iona
    -0.66
    andowski
    -0.66
     Bened
    -0.65
    pson
    -0.64
    infeld
    -0.64
    allo
    -0.62
    inery
    -0.61
    POSITIVE LOGITS
     lbs
    0.89
    ths
    0.86
     pounds
    0.83
    lbs
    0.80
     crore
    0.80
     ±
    0.77
     acres
    0.76
    /-
    0.76
     sq
    0.75
     yuan
    0.74
    Act Density 0.082%

    No Known Activations