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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and identifiers used in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fik
    -0.16
    orget
    -0.15
    idunt
    -0.13
    pread
    -0.13
    atra
    -0.13
    örü
    -0.13
    iid
    -0.13
    sink
    -0.13
    mium
    -0.13
    illet
    -0.13
    POSITIVE LOGITS
    1
    0.22
     Injury
    0.15
    и
    0.15
     injury
    0.15
     Barth
    0.15
     second
    0.14
     Trev
    0.14
     Lamb
    0.14
     final
    0.13
    991
    0.13
    Act Density 0.054%

    No Known Activations