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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media franchises or health-related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Entered
    -0.54
     maternity
    -0.51
     suffice
    -0.50
     redundancy
    -0.49
    >[
    -0.48
     decency
    -0.48
     she
    -0.48
     Haiti
    -0.47
     McCabe
    -0.46
     hers
    -0.46
    POSITIVE LOGITS
    ogy
    0.70
    rahim
    0.66
    ertodd
    0.66
    eous
    0.64
    tesy
    0.64
    ortment
    0.64
    orem
    0.63
    ecycle
    0.62
     pione
    0.61
    astery
    0.61
    Act Density 1.684%

    No Known Activations