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

    Neuronpedia

    INDEX
    Explanations

    advanced vocabulary words indicating sophisticated level of achievement or description

    oai_token-act-pair · gpt-3.5-turbo

    intense adjectives that convey significant qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.87
     unfocusedRange
    -0.73
     alot
    -0.69
     specifically
    -0.66
     obviously
    -0.65
     guiIcon
    -0.65
     predominantly
    -0.60
    ãĥ³ãĤ¸
    -0.59
     specific
    -0.59
     mainly
    -0.59
    POSITIVE LOGITS
    *.
    0.95
    .
    0.91
    .</
    0.88
    .<
    0.86
    !.
    0.82
    .'
    0.82
    .*
    0.81
    .:
    0.80
    '.
    0.73
    .?
    0.72
    Act Density 0.902%

    No Known Activations