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

    Neuronpedia

    INDEX
    Explanations

    numerical values or ratings in the context of language learning applications and historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascade
    -0.17
    erties
    -0.16
    ër
    -0.15
    جÙĦ
    -0.15
    ạc
    -0.14
    lingen
    -0.14
    innacle
    -0.14
    isy
    -0.14
    ULSE
    -0.14
    immers
    -0.14
    POSITIVE LOGITS
    toc
    0.19
    kin
    0.19
    ivar
    0.15
    2
    0.15
     ua
    0.15
    mys
    0.14
    ToObject
    0.14
     Hava
    0.14
     circa
    0.13
    *pow
    0.13
    Act Density 0.011%

    No Known Activations