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

    Neuronpedia

    INDEX
    Explanations

    references to profiles and representation in a collaborative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .tex
    -0.15
    _utilities
    -0.15
    allenge
    -0.14
    _caps
    -0.14
    arking
    -0.14
    .AutoScaleMode
    -0.14
    athi
    -0.13
     canh
    -0.13
    .HandlerFunc
    -0.13
    oldem
    -0.13
    POSITIVE LOGITS
    uisse
    0.15
    esti
    0.15
    oki
    0.15
    quito
    0.15
    ocks
    0.15
    avern
    0.14
     Pratt
    0.14
    omes
    0.14
    olin
    0.14
    egra
    0.14
    Act Density 0.149%

    No Known Activations