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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of counting or numerical value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "count" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.78
    antha
    -0.77
    ieties
    -0.74
    ovie
    -0.69
    insula
    -0.68
     prosec
    -0.66
    etheus
    -0.65
    azy
    -0.63
     educ
    -0.62
    utic
    -0.62
    POSITIVE LOGITS
    enance
    1.95
    downs
    0.85
    esses
    0.83
    ere
    0.83
    rified
    0.77
    ENCY
    0.76
    ess
    0.76
    ries
    0.71
    tops
    0.70
    stakes
    0.70
    Act Density 0.016%

    No Known Activations