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

    Neuronpedia

    INDEX
    Explanations

    questions and requests for information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.78
     considérons
    -0.59
    Folks
    -0.59
     leveraging
    -0.54
    ;-)
    -0.53
     magasiner
    -0.52
    DeleteBehavior
    -0.52
    middels
    -0.52
    <!--[
    -0.51
    cipar
    -0.51
    POSITIVE LOGITS
     arreg
    0.74
    ArgsConstructor
    0.70
     larmes
    0.67
     graças
    0.66
     arreglar
    0.65
     pitié
    0.65
     inútil
    0.65
     prouve
    0.64
     speranza
    0.64
     Anyways
    0.63
    Act Density 0.644%

    No Known Activations