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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating the start or initiation of an action

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating the initiation of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.78
    uably
    -0.78
    ortium
    -0.76
     Mellon
    -0.75
    quickShipAvailable
    -0.71
    士
    -0.69
    orthy
    -0.68
    isSpecialOrderable
    -0.66
    Availability
    -0.66
    Asia
    -0.66
    POSITIVE LOGITS
     yelling
    1.40
     shouting
    1.34
     chanting
    1.33
     screaming
    1.30
     pacing
    1.20
     banging
    1.20
     singing
    1.17
     crying
    1.15
     moaning
    1.14
     cursing
    1.14
    Act Density 0.063%

    No Known Activations