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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant transformations or alterations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oval
    -0.17
     behalf
    -0.14
    reet
    -0.14
    ÑĪÑĥ
    -0.13
     WCHAR
    -0.13
    ilit
    -0.13
    brook
    -0.13
    iese
    -0.13
    shift
    -0.13
    izont
    -0.13
    POSITIVE LOGITS
     into
    0.52
    into
    0.42
     Into
    0.39
    Into
    0.38
     INTO
    0.37
    _into
    0.35
     upside
    0.33
    .into
    0.28
     menjadi
    0.24
     turned
    0.23
    Act Density 0.018%

    No Known Activations