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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to political elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.77
    bably
    -0.77
    ciating
    -0.74
     strained
    -0.72
    orous
    -0.72
    uous
    -0.70
    icable
    -0.70
     minimized
    -0.66
    ienced
    -0.66
     suspended
    -0.66
    POSITIVE LOGITS
    estate
    0.95
    lance
    0.94
    stars
    0.85
    pointer
    0.85
    conference
    0.83
    group
    0.83
    division
    0.83
    points
    0.83
    amps
    0.81
    series
    0.80
    Act Density 0.209%

    No Known Activations