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

    Neuronpedia

    INDEX
    Explanations

    words related to counts or numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to counts or quantities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     separate
    -0.66
    ggie
    -0.65
    pez
    -0.65
    BIT
    -0.64
    oteric
    -0.64
     form
    -0.63
    urn
    -0.62
     pronoun
    -0.60
    uberty
    -0.59
    hra
    -0.59
    POSITIVE LOGITS
    enance
    1.30
    downs
    0.94
    esses
    0.89
    ess
    0.86
    ries
    0.86
    down
    0.79
    onia
    0.79
    count
    0.78
    âĦ¢:
    0.76
    sburg
    0.74
    Act Density 0.007%

    No Known Activations