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

    Neuronpedia

    INDEX
    Explanations

    references to compliance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     increí
    -0.58
     indígen
    -0.57
     للمعارف
    -0.55
     vectorielles
    -0.55
     CanadaChoose
    -0.54
    EndInit
    -0.54
    verwijspagina
    -0.54
     queſta
    -0.53
     miniaturka
    -0.51
     mariposas
    -0.51
    POSITIVE LOGITS
    Tro
    0.92
     Tro
    0.92
    tro
    0.82
     tro
    0.79
     Mo
    0.64
     TRO
    0.64
    Tur
    0.63
     reminds
    0.60
    osh
    0.59
    Mo
    0.56
    Act Density 0.152%

    No Known Activations