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

    Neuronpedia

    INDEX
    Explanations

    words indicating actions related to writing or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ase
    -0.07
    uda
    -0.06
    fs
    -0.06
    ats
    -0.06
     item
    -0.06
    elle
    -0.06
    -ass
    -0.06
    by
    -0.06
    hib
    -0.06
    '
    -0.06
    POSITIVE LOGITS
    Äįel
    0.09
    erli
    0.08
    -ahead
    0.08
     bahwa
    0.08
    çĽijåIJ¬é¡µéĿ¢
    0.08
    _perms
    0.07
    Ton
    0.07
     authDomain
    0.07
    >>)
    0.07
    .Encoding
    0.07
    Act Density 0.014%

    No Known Activations