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

    Neuronpedia

    INDEX
    Explanations

    terms related to leadership and authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _DOM
    -0.14
    ilo
    -0.14
     toler
    -0.14
    deps
    -0.14
    _Impl
    -0.14
    Fold
    -0.14
    olk
    -0.14
    _fold
    -0.14
    actal
    -0.13
    ille
    -0.13
    POSITIVE LOGITS
     Stre
    0.14
    stitution
    0.14
     reserv
    0.13
    come
    0.13
    IDA
    0.13
     Reserve
    0.13
    uce
    0.13
    ottage
    0.13
    wand
    0.13
     reserve
    0.13
    Act Density 0.288%

    No Known Activations