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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and their relationships in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.17
    ÃŃrk
    -0.16
    dfd
    -0.15
     LENG
    -0.15
    auce
    -0.14
    ftime
    -0.14
    bart
    -0.14
    Ã¶ÄŁ
    -0.14
    -sama
    -0.14
    ovit
    -0.14
    POSITIVE LOGITS
    /or
    0.22
     higher
    0.19
     possibly
    0.17
    respect
    0.17
    000
    0.17
    and
    0.17
    amp
    0.17
     optionally
    0.17
     again
    0.16
     latter
    0.16
    Act Density 0.126%

    No Known Activations