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

    Neuronpedia

    INDEX
    Explanations

    the variations of the pronoun "I" in different cases and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignon
    -0.16
    ignum
    -0.15
    adnÃŃ
    -0.15
    trecht
    -0.15
    wen
    -0.15
    baum
    -0.14
    åıij
    -0.14
    EMBER
    -0.14
    æľŁ
    -0.14
    reach
    -0.14
    POSITIVE LOGITS
    opard
    0.30
    alous
    0.28
    annie
    0.25
    eps
    0.23
    anner
    0.22
    unes
    0.21
     suis
    0.21
    annot
    0.20
    ann
    0.20
    ffc
    0.20
    Act Density 0.005%

    No Known Activations