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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the initiation of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.86
    uably
    -0.84
    obyl
    -0.74
     Mellon
    -0.72
    quickShipAvailable
    -0.70
     ancestors
    -0.70
    osate
    -0.70
     ancestor
    -0.67
    eros
    -0.66
     predecessors
    -0.66
    POSITIVE LOGITS
     yelling
    1.15
     pacing
    1.08
     screaming
    1.08
     shouting
    1.04
     banging
    1.03
     moaning
    1.00
     chanting
    1.00
     pounding
    0.98
     cursing
    0.95
     filming
    0.94
    Act Density 0.102%

    No Known Activations