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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix 'un' or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TINGS
    -0.16
    jee
    -0.15
    olson
    -0.15
    osis
    -0.14
    Forgot
    -0.14
    ULA
    -0.14
    elig
    -0.14
    \\/
    -0.14
    duct
    -0.13
    ëĭ´
    -0.13
    POSITIVE LOGITS
    swick
    0.16
     fortunate
    0.16
     otherwise
    0.15
    otherwise
    0.14
    à¸Ńà¸ĩ
    0.14
    label
    0.14
    ROUT
    0.14
    央
    0.14
     Narr
    0.14
     lucky
    0.14
    Act Density 0.032%

    No Known Activations