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

    Neuronpedia

    INDEX
    Explanations

    dash or hyphenated characters within negative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongan
    -0.16
    аков
    -0.14
    .grad
    -0.14
    282
    -0.14
    .epam
    -0.13
    icao
    -0.13
    lio
    -0.13
    edef
    -0.13
    ืà¹Ī
    -0.13
    ÑĤеÑĢ
    -0.13
    POSITIVE LOGITS
    s
    0.18
    a
    0.17
    erli
    0.16
    aÄĩ
    0.16
    apiro
    0.16
    er
    0.15
    enen
    0.15
    o
    0.15
    cth
    0.14
    es
    0.14
    Act Density 0.022%

    No Known Activations