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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iez
    -0.16
    301
    -0.15
     processes
    -0.14
     ag
    -0.14
    501
    -0.14
    erez
    -0.14
     worse
    -0.14
     zwar
    -0.14
    /Branch
    -0.14
     Processes
    -0.14
    POSITIVE LOGITS
    eming
    0.17
    PIX
    0.17
    /latest
    0.16
    Ñĩа
    0.16
    uen
    0.15
    addir
    0.15
    лий
    0.14
    пÑĢиклад
    0.14
     sorte
    0.14
    toi
    0.14
    Act Density 0.151%

    No Known Activations