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

    Neuronpedia

    INDEX
    Explanations

    references to flags and identifiers, especially in a programming or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Suc
    -0.62
     tute
    -0.52
     asce
    -0.51
     ci
    -0.50
    calar
    -0.48
    phism
    -0.47
     deform
    -0.47
    ercises
    -0.47
    ậc
    -0.46
     rubric
    -0.46
    POSITIVE LOGITS
     stolz
    0.65
     abstrait
    0.64
    proud
    0.63
     étrangère
    0.62
     chrétien
    0.61
     démocratique
    0.59
     électroniques
    0.58
     condamné
    0.56
     suspendu
    0.56
     llorar
    0.56
    Act Density 0.186%

    No Known Activations