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

    Neuronpedia

    INDEX
    Explanations

    links or references within content

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     both
    -0.53
    ........
    -0.52
     prosecutors
    -0.51
     scratch
    -0.50
     dock
    -0.49
    ......
    -0.48
     pictured
    -0.48
    olar
    -0.47
     nothing
    -0.47
    oping
    -0.47
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.73
    Disclaimer
    0.68
    ļéĨĴ
    0.65
    tumblr
    0.64
    é¾įå
    0.63
    assetsadobe
    0.62
     Annotations
    0.62
    adobe
    0.62
    ãĥ´
    0.61
    ©¶æ¥µ
    0.60
    Act Density 0.108%

    No Known Activations