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

    Neuronpedia

    INDEX
    Explanations

    phrasing that indicates uncertainty or the act of making statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igest
    -0.16
    etty
    -0.14
    eson
    -0.14
    uzzi
    -0.14
    gies
    -0.13
    alom
    -0.13
     desn
    -0.13
    etto
    -0.13
    illa
    -0.13
    udp
    -0.13
    POSITIVE LOGITS
     definit
    0.34
     definitely
    0.32
     beyond
    0.29
     definite
    0.28
     exact
    0.24
     Definitely
    0.24
     certainty
    0.24
     definitive
    0.24
     without
    0.23
    ç¡®
    0.22
    Act Density 0.176%

    No Known Activations