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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and constructs in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    altar
    -0.16
    ÃIJ
    -0.15
    elle
    -0.14
    áºŃt
    -0.14
     =č↵
    -0.14
     Butter
    -0.14
    ede
    -0.14
    asket
    -0.14
     brows
    -0.13
    iske
    -0.13
    POSITIVE LOGITS
    ":↵↵
    0.18
    ):↵↵
    0.17
     {↵↵
    0.17
     :↵↵
    0.16
    _nth
    0.16
    specialchars
    0.15
     ):↵↵
    0.15
     Eck
    0.15
     :↵
    0.15
     implements
    0.15
    Act Density 0.010%

    No Known Activations