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

    Neuronpedia

    INDEX
    Explanations

    instances of fleeing or escaping in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frei
    -0.16
     poil
    -0.15
    álo
    -0.14
    serter
    -0.14
     Noel
    -0.14
     Singles
    -0.13
     пеÑĢеб
    -0.13
    ulk
    -0.13
     Susp
    -0.13
    ัà¸įà¸į
    -0.13
    POSITIVE LOGITS
     khá»ıi
    0.22
    0.17
    zik
    0.15
    tight
    0.15
    azi
    0.14
    гл
    0.14
    entlich
    0.14
    .decorators
    0.14
    uluk
    0.14
    adir
    0.14
    Act Density 0.022%

    No Known Activations