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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    486
    -0.16
    анÑĮ
    -0.16
    éİ®
    -0.15
    leton
    -0.14
    caret
    -0.14
    deps
    -0.14
    hya
    -0.14
    eryl
    -0.14
    ernen
    -0.14
    fer
    -0.13
    POSITIVE LOGITS
    ñana
    0.15
     necessarily
    0.15
    \xaa
    0.15
    ibi
    0.15
     Tops
    0.14
    crew
    0.14
    StrictEqual
    0.14
    ÑŁ
    0.14
    warz
    0.14
    uben
    0.14
    Act Density 0.039%

    No Known Activations