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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "mis-" in words, indicating a focus on errors or incorrectness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amas
    -0.15
    ãĤ¤ãĥ¤
    -0.15
    aurus
    -0.14
    ylie
    -0.14
    ilee
    -0.14
     InitializeComponent
    -0.13
    fas
    -0.13
    /browse
    -0.13
    edia
    -0.13
    bedo
    -0.13
    POSITIVE LOGITS
    nock
    0.15
    rbrace
    0.15
    plit
    0.15
    rub
    0.14
    omers
    0.14
    MainThread
    0.14
    vla
    0.14
     useClass
    0.14
    ãĥ¼ãĥľ
    0.13
    placed
    0.13
    Act Density 0.009%

    No Known Activations