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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    sequences of dashes and special characters, possibly indicating formatting or transitions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leep
    -0.63
    ften
    -0.61
    cap
    -0.60
     decomp
    -0.60
    CW
    -0.60
    BW
    -0.59
    estic
    -0.59
    conn
    -0.58
    vert
    -0.58
    ously
    -0.58
    POSITIVE LOGITS
     âĢİ
    0.78
    \-
    0.70
     RTX
    0.68
     SOLD
    0.66
     Vulkan
    0.66
     Sold
    0.65
     Termin
    0.65
     Present
    0.62
     Dalai
    0.62
     Flare
    0.62
    Act Density 0.036%

    No Known Activations