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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speaking or acting on behalf of someone else

    oai_token-act-pair · gpt-3.5-turbo

    terms related to representation and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uve
    -0.71
    ãĤ£
    -0.70
    inctions
    -0.69
     Topic
    -0.68
    hig
    -0.65
    binary
    -0.64
    uesday
    -0.63
    aucus
    -0.60
    acan
    -0.60
    Bul
    -0.59
    POSITIVE LOGITS
     selves
    0.87
    steps
    0.85
    stretched
    0.80
     brethren
    0.80
     counterparts
    0.79
     Majesty
    0.79
     mortal
    0.71
    andering
    0.70
     sensibilities
    0.68
     cohorts
    0.68
    Act Density 0.192%

    No Known Activations