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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Hollins" and "Hob."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Revolution
    -0.74
    ept
    -0.69
     psy
    -0.65
    abolic
    -0.63
    ranean
    -0.63
    igmatic
    -0.62
     Sakuya
    -0.62
    rain
    -0.61
     Revolution
    -0.61
    rics
    -0.61
    POSITIVE LOGITS
    inson
    1.03
    aby
    0.94
    hots
    0.74
    ACK
    0.72
    crow
    0.71
    atility
    0.71
    estones
    0.70
    stakes
    0.70
    azar
    0.67
    idays
    0.67
    Act Density 0.054%

    No Known Activations