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

    Neuronpedia

    INDEX
    Explanations

    distinctions and differences in arguments or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isters
    -0.16
    nett
    -0.16
    REFIX
    -0.15
    MSN
    -0.14
    ÅĻez
    -0.14
    _STS
    -0.14
    iddet
    -0.14
    .utf
    -0.14
    okus
    -0.14
    urai
    -0.14
    POSITIVE LOGITS
    arta
    0.15
     Oro
    0.15
     esp
    0.15
    åī£
    0.14
    /classes
    0.14
    _DECLARE
    0.14
    cz
    0.14
    Ĵ
    0.14
    koa
    0.14
    icens
    0.14
    Act Density 0.126%

    No Known Activations