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

    Neuronpedia

    INDEX
    Explanations

    specific goals or objectives described in text

    oai_token-act-pair · gpt-3.5-turbo

    statements of objectives or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.82
     Warning
    -0.67
     glances
    -0.63
     Talks
    -0.60
     worries
    -0.60
    joy
    -0.60
     rests
    -0.60
    guards
    -0.60
     lurking
    -0.60
     bolted
    -0.59
    POSITIVE LOGITS
     educate
    1.27
     eradicate
    1.25
     recreate
    1.24
     create
    1.22
     establish
    1.19
     improve
    1.19
     maximize
    1.17
     replicate
    1.17
     eliminate
    1.16
     emulate
    1.15
    Act Density 0.140%

    No Known Activations