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

    Neuronpedia

    INDEX
    Explanations

    discourse markers and evaluative language in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.91
     betweenstory
    -0.90
     GenerationType
    -0.85
     defaultstate
    -0.84
    ftagPool
    -0.83
    ########.
    -0.81
    فایل‌لار
    -0.80
    tagext
    -0.79
    thâu
    -0.79
    Derbyniad
    -0.78
    POSITIVE LOGITS
    ↵↵
    0.61
     I
    0.60
    ,
    0.57
    :
    0.57
    ;
    0.52
    Билгалдахарш
    0.52
    -
    0.47
     ...
    0.45
    I
    0.44
    ?
    0.44
    Act Density 0.320%

    No Known Activations