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

    Neuronpedia

    INDEX
    Explanations

    code comments and special characters used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exact
    -0.17
    abee
    -0.15
     fo
    -0.15
    oader
    -0.15
     Con
    -0.15
    Exact
    -0.14
    unk
    -0.14
    acus
    -0.14
     conduit
    -0.14
    end
    -0.14
    POSITIVE LOGITS
    ÑĢава
    0.18
    iaux
    0.16
    weeney
    0.15
     wäh
    0.15
    otten
    0.15
     sucht
    0.14
    à¹Ĭ
    0.14
    ibble
    0.14
    avl
    0.14
    Ïģιά
    0.14
    Act Density 0.080%

    No Known Activations