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

    Neuronpedia

    INDEX
    Explanations

    non-English characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.16
    ÏĥÏĥ
    -0.15
     Thur
    -0.15
     Cyr
    -0.14
    otime
    -0.14
    _strdup
    -0.13
    urr
    -0.13
    ertext
    -0.13
    eÄį
    -0.13
    vette
    -0.13
    POSITIVE LOGITS
     BOOST
    0.36
    BOOST
    0.31
     typename
    0.29
     detail
    0.27
    traits
    0.27
     boost
    0.26
     traits
    0.25
     mpl
    0.25
    mpl
    0.24
     trait
    0.24
    Act Density 0.006%

    No Known Activations