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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to technology such as bandwidth speeds and error codes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numeric data or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arial
    -0.80
    boarding
    -0.73
    board
    -0.69
    mast
    -0.67
    many
    -0.65
    istically
    -0.65
    boards
    -0.63
    oult
    -0.63
     hope
    -0.60
     istg
    -0.59
    POSITIVE LOGITS
    é¾
    0.81
    æ©Ł
    0.80
    uador
    0.78
    nesday
    0.75
    stasy
    0.74
    202
    0.72
    halla
    0.69
    ļéĨĴ
    0.68
    011
    0.66
    707
    0.66
    Act Density 0.027%

    No Known Activations