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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sm
    -0.16
    528
    -0.15
    kop
    -0.15
    OCK
    -0.14
    laughter
    -0.14
     Fleming
    -0.14
    ey
    -0.14
    526
    -0.14
    IID
    -0.14
     Bow
    -0.13
    POSITIVE LOGITS
     tslib
    0.15
    jective
    0.15
    ieten
    0.14
     siè
    0.14
    uda
    0.14
    .Syntax
    0.14
    ’Ñıз
    0.14
    ằng
    0.14
    .nih
    0.13
    incinn
    0.13
    Act Density 1.193%

    No Known Activations