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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hack
    -0.16
    880
    -0.15
    _markup
    -0.14
    ooth
    -0.14
    wm
    -0.14
     Hate
    -0.14
     ÙģÙĪÙĦ
    -0.14
    Ã
    -0.13
     Throw
    -0.13
    ov
    -0.13
    POSITIVE LOGITS
    éné
    0.16
    mue
    0.15
     ãĥĬ
    0.14
    arest
    0.14
    .LookAndFeel
    0.14
    IRST
    0.14
    zs
    0.14
    ruk
    0.14
    perator
    0.13
    EMU
    0.13
    Act Density 0.094%

    No Known Activations