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

    Neuronpedia

    INDEX
    Explanations

    names of places and institutions

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.90
    etheless
    -0.90
    theless
    -0.77
    anwhile
    -0.76
     sanity
    -0.74
     physic
    -0.73
     parity
    -0.72
    76561
    -0.69
     trave
    -0.67
     compe
    -0.66
    POSITIVE LOGITS
    iest
    0.87
     Nebula
    0.85
    leys
    0.85
    onian
    0.83
    venth
    0.83
    hest
    0.82
    osphere
    0.82
    ospels
    0.78
     River
    0.77
    est
    0.75
    Act Density 0.373%

    No Known Activations