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

    Neuronpedia

    INDEX
    Explanations

    negations and their contexts in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ož
    -0.16
     Tits
    -0.15
     Bilim
    -0.15
    ãĥģ
    -0.15
    afort
    -0.15
    oeff
    -0.14
    _acquire
    -0.14
    ữu
    -0.14
    ertools
    -0.14
     lud
    -0.14
    POSITIVE LOGITS
     Milton
    0.17
    кÑĤа
    0.17
     Dude
    0.15
    ilton
    0.14
    udder
    0.14
    AMP
    0.14
    ddf
    0.14
     Cem
    0.14
    iangle
    0.14
     sincer
    0.14
    Act Density 0.019%

    No Known Activations