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

    Neuronpedia

    INDEX
    Explanations

    references to weapons and drug-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.78
     للمعارف
    -0.69
    ReusableCell
    -0.68
    الدراسه
    -0.66
     صوتيه
    -0.65
     nhàng
    -0.63
     дописавши
    -0.62
    省市镇
    -0.62
    tagHelperRunner
    -0.61
    apunov
    -0.60
    POSITIVE LOGITS
     assorted
    0.57
    expandindo
    0.54
     miscellaneous
    0.51
     sout
    0.50
     unusable
    0.49
     barked
    0.49
     racist
    0.47
     cried
    0.47
     assortment
    0.47
     Crying
    0.46
    Act Density 0.200%

    No Known Activations