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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and parameters used in data representation and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apl
    -0.16
    ead
    -0.16
    adol
    -0.15
    draft
    -0.15
    arias
    -0.15
    achi
    -0.15
     Cycl
    -0.14
    릿
    -0.14
     Cyr
    -0.14
    ÑĢÑı
    -0.14
    POSITIVE LOGITS
     pair
    0.21
     pairs
    0.21
     couple
    0.20
    _pair
    0.20
    pairs
    0.19
     duo
    0.19
    .pair
    0.19
    PAIR
    0.18
    _PAIR
    0.18
     Äijôi
    0.18
    Act Density 0.312%

    No Known Activations