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

    Neuronpedia

    INDEX
    Explanations

    references to page numbers or citations in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    board
    -0.15
     Pied
    -0.15
    ساÙĨ
    -0.14
    ixin
    -0.14
    ekk
    -0.14
    åĬ³
    -0.14
    ACHI
    -0.13
    lew
    -0.13
    addir
    -0.13
    ierge
    -0.13
    POSITIVE LOGITS
    utsch
    0.18
     Morton
    0.15
    thalm
    0.14
    ãĤ¹ãĥ¬
    0.14
    drž
    0.14
    istra
    0.13
    feld
    0.13
     iota
    0.13
    ilon
    0.13
    strand
    0.13
    Act Density 0.030%

    No Known Activations