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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \<^
    -0.95
    NUMX
    -0.92
    numerusform
    -0.89
     (\<
    -0.88
     tslint
    -0.84
     coö
    -0.82
    存于互联网档案馆
    -0.80
     كومونز
    -0.80
     iſt
    -0.79
    etheless
    -0.79
    POSITIVE LOGITS
    <bos>
    0.96
    .
    0.85
    ,
    0.74
    ?
    0.73
    a
    0.73
    !
    0.72
    »
    0.71
     ,
    0.70
    "
    0.70
    ↵
    0.70
    Act Density 0.784%

    No Known Activations