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

    Neuronpedia

    INDEX
    Explanations

    different forms of the word "cut."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hg
    -0.16
    him
    -0.15
    /out
    -0.15
    istor
    -0.15
    hood
    -0.15
    neh
    -0.14
    opa
    -0.14
    amiento
    -0.14
    outh
    -0.14
    hips
    -0.14
    POSITIVE LOGITS
    throat
    0.21
    aneous
    0.21
    ushman
    0.18
    backs
    0.18
    -cut
    0.17
    ting
    0.17
    cut
    0.16
    tings
    0.15
    ãĤ¥
    0.15
    scenes
    0.15
    Act Density 0.056%

    No Known Activations