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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing thoughts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or commas within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.99
    ļéĨĴ
    -0.76
    Associated
    -0.73
    STDOUT
    -0.67
    Detailed
    -0.64
    Requires
    -0.63
    SourceFile
    -0.63
    iosyncr
    -0.61
    Continue
    -0.60
    Merit
    -0.60
    POSITIVE LOGITS
     yeah
    1.39
     I
    1.18
     everybody
    1.11
     nobody
    1.10
     yes
    1.09
     we
    1.07
     you
    1.05
     they
    1.05
     somew
    1.04
     it
    1.02
    Act Density 0.253%

    No Known Activations