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

    Neuronpedia

    INDEX
    Explanations

    negations in statements about association or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tantôt
    -0.74
     vooral
    -0.69
     fallu
    -0.64
     ſeveral
    -0.63
     jopa
    -0.60
     hlavně
    -0.58
     ändå
    -0.57
     především
    -0.57
     cirka
    -0.56
     rarement
    -0.55
    POSITIVE LOGITS
     directly
    0.75
     necessarily
    0.73
     Италијани
    0.73
    EndGlobalSection
    0.70
     any
    0.69
     صوتيه
    0.69
     explicitly
    0.66
    AddHtmlAttribute
    0.64
    InjectAttribute
    0.61
    :✨
    0.60
    Act Density 0.729%

    No Known Activations