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

    Neuronpedia

    INDEX
    Explanations

    instances of colons and tags indicating content categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imb
    -0.15
    ë¥ĺ
    -0.15
    erry
    -0.15
    ince
    -0.15
    ιν
    -0.14
    riday
    -0.14
    ãĥªãĥ³ãĤ¯
    -0.14
    zilla
    -0.13
    ment
    -0.13
    uman
    -0.13
    POSITIVE LOGITS
     Maze
    0.15
     wij
    0.15
    hausen
    0.15
    chner
    0.14
     Maz
    0.14
    athing
    0.14
    ButtonModule
    0.14
    λή
    0.14
    EEK
    0.14
    oids
    0.14
    Act Density 0.012%

    No Known Activations