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

    Neuronpedia

    INDEX
    Explanations

    references to singular or unique items and their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vectorielles
    -0.73
     Vordergrund
    -0.62
     felb
    -0.58
     mukana
    -0.57
     gustaría
    -0.56
     vaikka
    -0.55
     Selecciona
    -0.55
     enemmän
    -0.54
     choisis
    -0.54
     tulee
    -0.54
    POSITIVE LOGITS
     thing
    0.86
     remaining
    0.79
     ever
    0.73
     imaginable
    0.71
    remaining
    0.70
     known
    0.67
    MigrationBuilder
    0.67
    唯一
    0.66
     Chwiliwch
    0.66
     Thing
    0.65
    Act Density 0.122%

    No Known Activations