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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atical
    -0.68
    ghai
    -0.67
    acts
    -0.67
    rous
    -0.65
    yrinth
    -0.64
    inition
    -0.63
    fare
    -0.62
    ographies
    -0.62
    lance
    -0.61
     Volks
    -0.60
    POSITIVE LOGITS
    '
    1.73
    mith
    1.60
    hip
    1.42
    hips
    1.38
    ']
    1.35
    nyder
    1.23
    haw
    1.22
    kaya
    1.20
    pring
    1.19
    peed
    1.19
    Act Density 0.175%

    No Known Activations