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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical counts or values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "count" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.77
     Palestin
    -0.74
     Eden
    -0.69
    NetMessage
    -0.69
    ieties
    -0.68
     Harbor
    -0.67
    ovie
    -0.66
    ©¶æ
    -0.66
     obser
    -0.65
     inflamm
    -0.64
    POSITIVE LOGITS
    enance
    1.85
    downs
    1.19
    esses
    0.89
    ess
    0.88
    down
    0.88
    ere
    0.86
    ries
    0.85
    sheets
    0.83
    tops
    0.82
    stakes
    0.80
    Act Density 0.015%

    No Known Activations