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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names like "Sofia" or "Alcide"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ange
    -0.74
    eer
    -0.71
     Arbor
    -0.70
     contrace
    -0.68
     newsletters
    -0.68
     Held
    -0.67
    backer
    -0.66
     WRITE
    -0.66
     Gardens
    -0.66
     externalToEVAOnly
    -0.65
    POSITIVE LOGITS
    ocom
    0.93
    oha
    0.88
    iltration
    0.81
    riad
    0.80
    azar
    0.80
    obar
    0.79
    romy
    0.79
    osate
    0.76
    rolet
    0.76
    omon
    0.75
    Act Density 0.029%

    No Known Activations