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

    Neuronpedia

    INDEX
    Explanations

    phrases related to choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EEDED
    -0.07
    uzzi
    -0.06
    andre
    -0.06
    ãĥĥãĤ·ãĥ¥
    -0.06
    kir
    -0.06
    fon
    -0.06
    acin
    -0.06
    inç
    -0.06
    rupa
    -0.06
    ilst
    -0.06
    POSITIVE LOGITS
     between
    0.10
     of
    0.09
    ality
    0.09
     whether
    0.09
     giữa
    0.07
     междÑĥ
    0.07
    whether
    0.07
     Between
    0.07
    æĺ¯åIJ¦
    0.07
    als
    0.07
    Act Density 0.005%

    No Known Activations