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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal arguments or considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kinda
    -0.53
     gonna
    -0.44
     thru
    -0.40
     anyways
    -0.39
    #+#
    -0.39
     heisst
    -0.38
     πως
    -0.37
    เค้า
    -0.37
     ‘
    -0.36
     alot
    -0.35
    POSITIVE LOGITS
     ویکی‌پدی
    0.60
     Ministers
    0.59
    elemField
    0.55
     hon
    0.53
     ministres
    0.53
    そのような
    0.52
    Mr
    0.51
    featureID
    0.51
    Наводи
    0.50
    Tetapi
    0.50
    Act Density 0.085%

    No Known Activations