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

    Neuronpedia

    INDEX
    Explanations

    the name "Sirhan" with varying levels of activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific name, "Han"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     smarter
    -0.71
    ISION
    -0.64
     Clicker
    -0.63
     Replay
    -0.63
     Sector
    -0.63
    psey
    -0.60
    ãĥ¯
    -0.60
     Eucl
    -0.58
    nesday
    -0.57
     JPEG
    -0.57
    POSITIVE LOGITS
    igans
    1.18
    igan
    0.92
    mare
    0.91
    azard
    0.90
    abal
    0.87
    ttp
    0.86
    ild
    0.86
    adan
    0.85
    ovember
    0.84
    quin
    0.83
    Act Density 0.029%

    No Known Activations