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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and places, particularly those starting with "Ras" and related figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.68
    ovies
    -0.67
    alach
    -0.67
    anooga
    -0.67
    alities
    -0.66
     Hindi
    -0.66
    lehem
    -0.66
     Corpus
    -0.65
    ype
    -0.63
    terson
    -0.61
    POSITIVE LOGITS
    senal
    1.27
    cliffe
    0.89
    uling
    0.84
    ulic
    0.82
    hod
    0.78
    Studio
    0.76
     Runner
    0.75
    Downloadha
    0.73
    spective
    0.72
     Racer
    0.71
    Act Density 0.147%

    No Known Activations