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

    Neuronpedia

    INDEX
    Explanations

    references to labeling or categorizing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abh
    -0.15
    angler
    -0.15
    eny
    -0.15
    apur
    -0.15
    arc
    -0.14
    ero
    -0.14
    resse
    -0.13
    239
    -0.13
    CF
    -0.13
    /environment
    -0.13
    POSITIVE LOGITS
    ewolf
    0.19
    coon
    0.18
    ieten
    0.17
    иÑĢÑĥ
    0.16
    ged
    0.15
    ettle
    0.15
    BeginInit
    0.15
    à¤ķरण
    0.15
     -*-č↵
    0.14
    ioni
    0.14
    Act Density 0.013%

    No Known Activations