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

    Neuronpedia

    INDEX
    Explanations

    sentences that discuss or describe specific topics or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lbrace
    -0.15
    OTES
    -0.15
     bir
    -0.14
    Ñĥж
    -0.14
    _INLINE
    -0.14
    _simps
    -0.14
    anten
    -0.14
    ãĥªãĥ¼
    -0.14
    bir
    -0.13
    ATEST
    -0.13
    POSITIVE LOGITS
     Bookmark
    0.34
    Bookmark
    0.21
    uzzi
    0.20
    åĭ
    0.17
     bookmark
    0.16
     RSS
    0.15
    omit
    0.15
    RSS
    0.15
    ::.
    0.15
    bookmark
    0.15
    Act Density 0.007%

    No Known Activations