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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Bro"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Bro" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneous
    -0.72
    URA
    -0.64
     Nadu
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.62
    uality
    -0.61
     Centauri
    -0.60
     repetition
    -0.60
     Dull
    -0.60
    aries
    -0.59
     liberty
    -0.59
    POSITIVE LOGITS
    ccoli
    1.26
    oks
    1.11
    dy
    1.08
    gue
    1.07
    thel
    1.05
    chet
    1.04
    kens
    1.03
    keye
    1.01
    thren
    0.96
    etooth
    0.93
    Act Density 0.029%

    No Known Activations