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

    Neuronpedia

    INDEX
    Explanations

    URLs leading to external web pages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "t"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.92
     destro
    -0.84
    ħĭ
    -0.80
    ĪĴ
    -0.75
    EStream
    -0.75
     Skydragon
    -0.71
     behavi
    -0.71
     exha
    -0.70
     tremend
    -0.69
     hemor
    -0.68
    POSITIVE LOGITS
    ractor
    1.24
    ribute
    1.22
    ract
    1.21
    uple
    1.20
    ruck
    1.19
    ruly
    1.18
    asks
    1.15
    aken
    1.14
    otally
    1.13
    roph
    1.13
    Act Density 0.065%

    No Known Activations