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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of periods, indicating sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihar
    -0.82
    wcs
    -0.79
     glim
    -0.74
    perty
    -0.72
    metadata
    -0.71
    inarily
    -0.69
    alysed
    -0.69
    ylum
    -0.68
     bandits
    -0.67
    ichever
    -0.65
    POSITIVE LOGITS
    Gray
    0.79
     Myers
    0.75
    assetsadobe
    0.73
     Olson
    0.72
    tein
    0.71
     York
    0.70
     Baker
    0.70
     Ack
    0.70
    K
    0.69
     Happ
    0.69
    Act Density 0.052%

    No Known Activations