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

    Neuronpedia

    INDEX
    Explanations

    occurrences of apostrophized words, indicating possessive or contracted forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.27
    Ùĩ
    -0.16
    tti
    -0.15
    owski
    -0.14
    952
    -0.14
    нг
    -0.14
    YNAM
    -0.14
    ombat
    -0.14
    igner
    -0.14
    760
    -0.13
    POSITIVE LOGITS
    richt
    0.15
    them
    0.14
    ık
    0.13
    ephir
    0.13
    waves
    0.13
    imately
    0.12
    -navbar
    0.12
     Doch
    0.12
    nyder
    0.12
    _scal
    0.12
    Act Density 0.021%

    No Known Activations