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

    Neuronpedia

    INDEX
    Explanations

    years and events in history

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the conclusion of events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.78
    lain
    -0.70
    vous
    -0.68
    caster
    -0.67
    hid
    -0.66
    upper
    -0.65
    oun
    -0.63
    wine
    -0.63
     formerly
    -0.63
    hips
    -0.62
    POSITIVE LOGITS
     tears
    0.79
     turnovers
    0.68
     disappointment
    0.68
     irreversible
    0.67
     humiliating
    0.67
     bloodshed
    0.66
     cliff
    0.66
     completion
    0.66
     tragedy
    0.65
     bankruptcy
    0.65
    Act Density 0.127%

    No Known Activations