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

    Neuronpedia

    INDEX
    Explanations

    occurrences of formatting symbols and their emphasis in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rez
    -0.15
    isini
    -0.15
    elper
    -0.14
    ØŃÙĤ
    -0.14
    iras
    -0.14
    acon
    -0.14
    ocking
    -0.14
    ulis
    -0.14
    bih
    -0.14
    isable
    -0.13
    POSITIVE LOGITS
     Entire
    0.15
     exactly
    0.15
    _refl
    0.15
     actual
    0.14
    736
    0.14
    ¥
    0.13
     particular
    0.13
     entire
    0.13
    egas
    0.13
     entirely
    0.13
    Act Density 0.051%

    No Known Activations