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

    Neuronpedia

    INDEX
    Explanations

    sequences that start with "L" or "l" followed by a single-digit or sequences that contain "water has become more"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol appearing in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.71
    é¾įå¥ij士
    -0.71
    ãĥ¼ãĤ¯
    -0.66
    smanship
    -0.65
     âĶľ
    -0.65
    ģĸ
    -0.65
     pleasure
    -0.64
     Primal
    -0.64
    gerald
    -0.64
    POSITIVE LOGITS
    aughter
    1.17
    yrics
    1.15
    IGHT
    1.12
    ateral
    1.12
    UX
    1.11
    ocker
    1.10
    ONDON
    1.07
    adders
    1.07
    isted
    1.07
    anc
    1.07
    Act Density 0.033%

    No Known Activations