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

    Neuronpedia

    INDEX
    Explanations

    references to significant concepts or entities indicating importance or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inee
    -0.16
     Bij
    -0.15
    ifier
    -0.15
    arov
    -0.15
     Mond
    -0.14
    IFIER
    -0.14
    ophysical
    -0.14
     EA
    -0.14
     .
    -0.14
    ajes
    -0.14
    POSITIVE LOGITS
    urette
    0.17
    ëŀij
    0.16
    TRL
    0.16
    trie
    0.15
    /Instruction
    0.15
    füg
    0.15
    pac
    0.14
    åľ¨çº¿éĺħ读
    0.14
    pent
    0.14
    usement
    0.14
    Act Density 0.000%

    No Known Activations