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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the establishment or founding of organizations, entities, or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dos
    -0.62
     Surface
    -0.60
     locker
    -0.60
     stroke
    -0.59
     blot
    -0.59
     wash
    -0.57
    TPP
    -0.57
     discrep
    -0.56
    how
    -0.56
    Pro
    -0.56
    POSITIVE LOGITS
    ablished
    0.86
     anew
    0.85
     by
    0.76
    quartered
    0.76
    lehem
    0.74
    prising
    0.69
     headquartered
    0.69
    hement
    0.67
    terday
    0.67
     Seym
    0.65
    Act Density 0.087%

    No Known Activations