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

    Neuronpedia

    INDEX
    Explanations

    Greek symbols or technical terms related to mathematics

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols representing complex functions or parameters in mathematics or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.74
    ilage
    -0.73
    voy
    -0.71
    peed
    -0.68
    hower
    -0.68
     Coke
    -0.67
     Mouth
    -0.67
    ierrez
    -0.65
     Blanc
    -0.65
     Ada
    -0.65
    POSITIVE LOGITS
    α
    1.69
    ι
    1.69
    ο
    1.57
    ÏĦ
    1.50
    Ï
    1.46
    β
    1.41
    ε
    1.39
    κ
    1.35
    ν
    1.33
    Ïī
    1.30
    Act Density 0.009%

    No Known Activations