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

    Neuronpedia

    INDEX
    Explanations

    phrases related to offerings or options

    oai_token-act-pair · gpt-3.5-turbo

    terms related to services and offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pace
    -0.63
     rusty
    -0.62
    alg
    -0.62
    brance
    -0.61
     circle
    -0.60
    riter
    -0.58
     tox
    -0.57
     tangled
    -0.56
     simultane
    -0.56
    Hyper
    -0.55
    POSITIVE LOGITS
     offers
    3.38
     offer
    2.25
     Offer
    1.80
     invites
    1.77
     promises
    1.70
     offered
    1.68
     provides
    1.66
     boasts
    1.62
    offer
    1.60
     offerings
    1.60
    Act Density 0.010%

    No Known Activations