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

    Neuronpedia

    INDEX
    Explanations

    verbal threats or warnings

    oai_token-act-pair · gpt-3.5-turbo

    instances of threats or intimidation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.75
    pite
    -0.69
    points
    -0.63
    IED
    -0.62
    pointers
    -0.62
    anticipated
    -0.59
    quartered
    -0.59
     è£ıè¦ļéĨĴ
    -0.58
     salient
    -0.57
    bable
    -0.57
    POSITIVE LOGITS
     donate
    1.10
     dismantle
    1.10
     give
    1.03
     dedicate
    1.01
     amend
    1.01
     bring
    1.01
     leave
    1.00
     eliminate
    0.99
     recreate
    0.98
     settle
    0.96
    Act Density 0.121%

    No Known Activations