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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amin
    -0.15
    ches
    -0.15
    sr
    -0.15
    agna
    -0.15
     div
    -0.15
    BA
    -0.15
    fr
    -0.15
    ág
    -0.14
    umes
    -0.14
    eyen
    -0.14
    POSITIVE LOGITS
    gebn
    0.16
    alaria
    0.15
    azo
    0.14
     Gab
    0.14
    Ħ
    0.13
    оваÑĢ
    0.13
    ãĥ³ãĤ¬
    0.13
     Perc
    0.13
    ıyı
    0.13
    wake
    0.13
    Act Density 0.233%

    No Known Activations