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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Shadow" with varying levels of prominence in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "Shadow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.91
    keye
    -0.79
    artney
    -0.75
    OPLE
    -0.75
    secut
    -0.72
    awaru
    -0.71
    elson
    -0.71
    olics
    -0.68
    perature
    -0.68
    olid
    -0.68
    POSITIVE LOGITS
     Shadow
    1.15
    moon
    0.96
    Shadow
    0.92
     Shadows
    0.91
    hawk
    0.88
    crow
    0.85
     Phantom
    0.85
    loo
    0.83
     Sneak
    0.80
     Pupp
    0.79
    Act Density 0.004%

    No Known Activations