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

    Neuronpedia

    INDEX
    Explanations

    occurrences of significant keywords or phrases indicating various forms of notices, challenges, or constraints in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.17
    ccc
    -0.16
    út
    -0.15
    ghan
    -0.15
    äm
    -0.14
     Florence
    -0.14
    orda
    -0.14
    opsis
    -0.14
    CCC
    -0.14
    conds
    -0.14
    POSITIVE LOGITS
    ono
    0.16
    610
    0.15
     dun
    0.15
    missive
    0.15
    pit
    0.14
    ONO
    0.14
    åı¸
    0.14
    elin
    0.14
    pawn
    0.14
    Ïĥκε
    0.14
    Act Density 0.001%

    No Known Activations