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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing significance and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERING
    -0.16
    nad
    -0.15
    egr
    -0.14
    éĩ
    -0.14
    ÅĻes
    -0.14
    luv
    -0.14
    eri
    -0.14
    .EMPTY
    -0.14
    á»ģn
    -0.14
    ardon
    -0.14
    POSITIVE LOGITS
    already
    0.15
    eur
    0.14
     already
    0.14
    lingen
    0.14
    ables
    0.14
    eper
    0.14
     Bench
    0.14
    ÏĦί
    0.14
    ZA
    0.14
     Ur
    0.14
    Act Density 0.071%

    No Known Activations