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

    Neuronpedia

    INDEX
    Explanations

    the word "Not" in various contexts, usually indicating negation or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ite
    -0.15
    486
    -0.15
    muz
    -0.14
    .Expression
    -0.13
    istra
    -0.13
    rame
    -0.13
    itele
    -0.13
    á»ĥn
    -0.13
    ury
    -0.13
    iÄħ
    -0.13
    POSITIVE LOGITS
     necessarily
    0.18
    ungs
    0.15
    //=
    0.14
    _WM
    0.14
    tingham
    0.14
    ido
    0.14
    olas
    0.14
    licer
    0.13
    zsche
    0.13
    icers
    0.13
    Act Density 0.038%

    No Known Activations