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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "hundred"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hundred"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elight
    -0.65
    Lab
    -0.62
    added
    -0.61
    TM
    -0.59
     Also
    -0.59
     Emer
    -0.57
     aka
    -0.56
    hes
    -0.56
     both
    -0.55
     Posted
    -0.55
    POSITIVE LOGITS
     hundred
    3.62
     thousand
    2.69
     Hundred
    2.21
     dozen
    2.09
    undred
    1.97
     fifty
    1.70
     eighty
    1.67
     seventy
    1.57
     ninety
    1.56
     sixty
    1.51
    Act Density 0.015%

    No Known Activations