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

    Neuronpedia

    INDEX
    Explanations

    negations and words reflecting denial or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Marathon
    -0.48
     Dress
    -0.46
     oslo
    -0.43
    ensä
    -0.43
    Transcript
    -0.43
     dress
    -0.42
    っけ
    -0.42
     lifted
    -0.41
    ometrial
    -0.41
    лә
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.97
    новниш
    0.91
    //
    0.90
     يتيمه
    0.89
    mybatisplus
    0.85
    modb
    0.75
    شهاد
    0.73
     Normdatei
    0.72
    /**
    0.72
    GEBURTSDATUM
    0.71
    Act Density 0.554%

    No Known Activations