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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong emotional reactions or assessments, particularly related to disappointment or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mektedir
    -0.98
    INSEE
    -0.69
    maktadır
    -0.69
     CANNOT
    -0.60
    KeyEvent
    -0.60
    才可以
    -0.60
    Diweddarwch
    -0.60
    rsiniz
    -0.60
    mıştır
    -0.60
    AutoScaleMode
    -0.58
    POSITIVE LOGITS
     gotta
    1.09
     outta
    1.01
     تانيه
    1.01
     gonna
    1.00
     somethin
    0.97
     GONNA
    0.88
     talkin
    0.86
     nothin
    0.84
    Gonna
    0.82
    Gimme
    0.82
    Act Density 0.383%

    No Known Activations