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

    Neuronpedia

    INDEX
    Explanations

    instances of the number "two" within a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "two."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asta
    -0.79
    ugu
    -0.76
    amaru
    -0.69
    ovi
    -0.69
    awaru
    -0.69
    rir
    -0.67
    rolet
    -0.65
    ubs
    -0.65
    inkle
    -0.64
    aukee
    -0.64
    POSITIVE LOGITS
     thirds
    1.39
     halves
    0.98
     dozen
    0.98
     weeks
    0.95
    teen
    0.88
     hundred
    0.86
    teenth
    0.85
    fold
    0.84
     decades
    0.83
    een
    0.82
    Act Density 0.071%

    No Known Activations