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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize enhancement or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullan
    -0.17
     disaster
    -0.15
    cess
    -0.14
    azu
    -0.14
    uhe
    -0.14
    nt
    -0.13
    &E
    -0.13
     ha
    -0.13
    olls
    -0.13
     Fulton
    -0.13
    POSITIVE LOGITS
     doubly
    0.44
     cÃłng
    0.33
     extra
    0.31
     ëįĶìļ±
    0.27
     EXTRA
    0.27
     EVEN
    0.25
    -extra
    0.25
    extra
    0.24
    _extra
    0.24
     Extra
    0.24
    Act Density 0.120%

    No Known Activations