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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scaleFactor
    -0.14
     Whoever
    -0.14
     ấy
    -0.14
    ãģĵãģ¨ãģ«
    -0.14
     bulunan
    -0.13
    तम
    -0.13
    -même
    -0.13
    anto
    -0.13
     thereof
    -0.13
     dessa
    -0.13
    POSITIVE LOGITS
     why
    0.36
     how
    0.33
     where
    0.29
     precisely
    0.28
    why
    0.26
     what
    0.26
    how
    0.22
     exactly
    0.22
     when
    0.21
     precis
    0.21
    Act Density 0.084%

    No Known Activations