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

    Neuronpedia

    INDEX
    Explanations

    words indicating contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ó
    -0.15
    UIL
    -0.14
     NÄĽm
    -0.14
    ska
    -0.14
     Deg
    -0.14
    oslav
    -0.14
    RTL
    -0.14
    ystone
    -0.13
    opers
    -0.13
     Rudd
    -0.13
    POSITIVE LOGITS
    aras
    0.15
    gone
    0.15
    earn
    0.15
    ÏĦÏİ
    0.15
    Uploaded
    0.14
    æ½®
    0.14
     hare
    0.14
    TOR
    0.13
    StackTrace
    0.13
    atorium
    0.13
    Act Density 0.198%

    No Known Activations