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

    Neuronpedia

    INDEX
    Explanations

    quantities of a specific number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hundred" and related numerical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obal
    -0.71
    rang
    -0.63
    hra
    -0.63
    beh
    -0.61
    kamp
    -0.61
    shows
    -0.60
     Lover
    -0.60
     shortened
    -0.59
     Noir
    -0.59
    opens
    -0.58
    POSITIVE LOGITS
     thousand
    1.28
    ousand
    1.10
     Thousand
    1.06
     miles
    0.92
     metres
    0.91
     dollars
    0.91
     acres
    0.91
    undred
    0.90
     pounds
    0.88
    ths
    0.88
    Act Density 0.020%

    No Known Activations