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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or the potential for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GLOSS
    -0.16
    ucs
    -0.15
    illet
    -0.15
    erville
    -0.14
    nez
    -0.14
    аÑĢаÑĤ
    -0.14
    HEET
    -0.14
    icken
    -0.14
    র
    -0.14
    ethoven
    -0.14
    POSITIVE LOGITS
     decent
    0.17
    weg
    0.16
     thr
    0.15
    allah
    0.15
    alla
    0.15
    дов
    0.15
     Universal
    0.14
    umerator
    0.14
     waterproof
    0.14
    amd
    0.14
    Act Density 0.053%

    No Known Activations