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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new topics or sections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.76
     tartalomajánló
    -0.64
     kasarigan
    -0.64
     مشين
    -0.58
    دانشنامهٔ
    -0.55
    AndEndTag
    -0.52
    windowFixed
    -0.51
     par
    -0.49
    optionalTypeArgs
    -0.49
    UnusedPrivate
    -0.47
    POSITIVE LOGITS
     pleaſure
    0.88
     himſelf
    0.88
    ſelves
    0.87
     ſmall
    0.86
     Jefus
    0.86
     myſelf
    0.86
     themſelves
    0.85
     purpoſe
    0.85
     houſe
    0.83
    ſelf
    0.82
    Act Density 0.165%

    No Known Activations