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

    Neuronpedia

    INDEX
    Explanations

    instances of model names or technical terms with numbers in them

    oai_token-act-pair · gpt-3.5-turbo

    specific product names and brand identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =]
    -0.78
    Ô
    -0.74
    etimes
    -0.71
    é¾įå¥ij士
    -0.69
    ãģĨ
    -0.69
    appropriate
    -0.67
    abet
    -0.66
    occupied
    -0.66
    obar
    -0.66
    ocrates
    -0.65
    POSITIVE LOGITS
     consists
    1.19
     comprises
    1.11
     represents
    1.11
     operates
    1.10
     incorporates
    1.09
     resembles
    1.09
     utilizes
    1.07
     is
    1.07
     relies
    1.04
     differs
    1.04
    Act Density 0.394%

    No Known Activations