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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ë²Į
    -0.15
     trough
    -0.14
    fir
    -0.14
    ilde
    -0.14
    mov
    -0.14
     Rif
    -0.14
    814
    -0.13
    rdf
    -0.13
    chwitz
    -0.13
    papers
    -0.13
    POSITIVE LOGITS
     basis
    0.17
    ursal
    0.16
     occasion
    0.16
    ushima
    0.15
     behalf
    0.15
    look
    0.15
    auer
    0.15
    é§Ĩ
    0.15
    OUR
    0.15
     grounds
    0.14
    Act Density 0.292%

    No Known Activations