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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or variability in actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     narr
    -0.16
    LEGRO
    -0.16
    trak
    -0.14
     Gazette
    -0.14
    eria
    -0.14
    apat
    -0.14
    oucher
    -0.14
    èĬĻ
    -0.14
    Castle
    -0.14
    ancia
    -0.13
    POSITIVE LOGITS
    elite
    0.14
    opot
    0.14
    osity
    0.14
    contres
    0.14
    esiz
    0.13
     tolik
    0.13
    -errors
    0.13
    issy
    0.13
    itorio
    0.13
    ogh
    0.13
    Act Density 0.118%

    No Known Activations