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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or contrasting statements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.75
    -,
    -0.69
    arily
    -0.63
    ãĤ´
    -0.63
    Detailed
    -0.63
    MpServer
    -0.62
    ,...
    -0.62
    ļéĨĴ
    -0.60
    inar
    -0.60
    Includes
    -0.60
    POSITIVE LOGITS
     however
    1.20
     though
    1.04
     therefore
    0.88
     it
    0.87
     although
    0.86
     we
    0.82
     moreover
    0.80
     yes
    0.78
     there
    0.78
     they
    0.76
    Act Density 0.253%

    No Known Activations