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

    Neuronpedia

    INDEX
    Explanations

    numerical values with multiple digits

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly large numbers and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antha
    -0.72
    boards
    -0.70
    arial
    -0.68
    moon
    -0.67
    pled
    -0.66
    boarding
    -0.66
    many
    -0.66
    vol
    -0.66
    saf
    -0.64
    board
    -0.63
    POSITIVE LOGITS
    é¾
    0.81
    TION
    0.76
    374
    0.72
    202
    0.72
    685
    0.72
    804
    0.72
    208
    0.72
    807
    0.70
    stasy
    0.70
    203
    0.69
    Act Density 0.027%

    No Known Activations