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

    Neuronpedia

    INDEX
    Explanations

    certain phrases indicating conditionality or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     volontaire
    -0.54
     mourir
    -0.54
    ندما
    -0.54
     preuve
    -0.54
     pulito
    -0.54
     aquello
    -0.49
     utilisées
    -0.49
    när
    -0.49
     dépass
    -0.48
     auraient
    -0.48
    POSITIVE LOGITS
    CPtr
    0.84
     utafitiHapana
    0.70
    NameInMap
    0.70
    WebVitals
    0.69
    principalColumn
    0.65
    ArrowToggle
    0.65
    Portail
    0.64
     CanadaChoose
    0.63
     Exacts
    0.63
     EconPapers
    0.62
    Act Density 0.294%

    No Known Activations