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

    Neuronpedia

    INDEX
    Explanations

    references to significant numbers or statistics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olute
    -0.17
    opensource
    -0.15
    éĸī
    -0.14
    ÅĻet
    -0.14
     luder
    -0.14
    ãĥ³ãĥĨãĤ£
    -0.14
    HeaderCode
    -0.13
    yonel
    -0.13
    ãģ¤ãģ¶
    -0.13
    celed
    -0.13
    POSITIVE LOGITS
     Alone
    0.21
    alone
    0.20
     alone
    0.20
    ird
    0.19
    ement
    0.17
    254
    0.16
    asp
    0.15
    st
    0.15
    kos
    0.15
    kowski
    0.15
    Act Density 0.019%

    No Known Activations