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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specificity and precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ต่างๆ
    -0.43
     gröss
    -0.42
     múltiples
    -0.42
    อื่น
    -0.41
     otros
    -0.41
     multiple
    -0.41
     africaine
    -0.39
     ansatte
    -0.39
     other
    -0.39
    其他
    -0.39
    POSITIVE LOGITS
     exactly
    0.82
     EXACTLY
    0.79
    exactly
    0.77
     виправивши
    0.76
    Exactly
    0.75
     Exactly
    0.73
     precisely
    0.73
    Genau
    0.68
     JUST
    0.68
     exatamente
    0.67
    Act Density 0.182%

    No Known Activations