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

    Neuronpedia

    INDEX
    Explanations

    instances of notes or annotations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.58
     للمعارف
    -0.54
    нгред
    -0.50
     مشين
    -0.49
     "..\..\..\
    -0.49
    كويكب
    -0.48
    endcsname
    -0.48
    werty
    -0.47
    +#+#
    -0.46
    ArgsConstructor
    -0.45
    POSITIVE LOGITS
    Note
    0.74
     note
    0.72
     Note
    0.70
    note
    0.69
    NOTE
    0.63
    Remarque
    0.61
     NOTE
    0.60
    注意
    0.59
    caution
    0.58
     caution
    0.54
    Act Density 0.368%

    No Known Activations