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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exceptions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _DIP
    -0.15
    enberg
    -0.15
    imedia
    -0.15
    ÑĩÑĥк
    -0.14
    лом
    -0.14
    olson
    -0.14
    oze
    -0.14
    ại
    -0.14
    nett
    -0.14
    одаÑĢ
    -0.14
    POSITIVE LOGITS
     naturally
    0.91
     Naturally
    0.79
     natürlich
    0.75
     natuur
    0.66
     obviously
    0.66
    å½ĵçĦ¶
    0.62
    aturally
    0.56
     samozÅĻejmÄĽ
    0.52
     Obviously
    0.52
     конеÑĩно
    0.52
    Act Density 0.663%

    No Known Activations