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

    Neuronpedia

    INDEX
    Explanations

    words associated with news and current events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.82
    rolet
    -0.81
    ãĤ¨ãĥ«
    -0.74
    aukee
    -0.71
    eteria
    -0.70
    quished
    -0.69
    ļéĨĴ
    -0.68
    maxwell
    -0.67
    mouth
    -0.66
    ROR
    -0.65
    POSITIVE LOGITS
     it
    1.04
     coupled
    1.02
     chances
    1.00
     why
    0.97
     shouldn
    0.96
     we
    0.90
     surely
    0.88
     expect
    0.86
     there
    0.81
     figuring
    0.78
    Act Density 0.240%

    No Known Activations