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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion and perspectives on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elemField
    -0.69
    theoremstyle
    -0.68
     ModelExpression
    -0.68
     estekak
    -0.66
    apimachinery
    -0.63
     MenuView
    -0.61
    WithMany
    -0.60
     Roskov
    -0.59
    دانشنامهٔ
    -0.57
     betweenstory
    -0.56
    POSITIVE LOGITS
    ')],
    0.48
    썬
    0.48
    "?>
    0.47
    ){}
    0.47
    awtextra
    0.47
     immerhin
    0.46
    لينكات
    0.46
     tqdm
    0.44
    ='')
    0.44
     Danach
    0.44
    Act Density 0.375%

    No Known Activations