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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or intentions done for someone else's benefit

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or contributions made by individuals on behalf of others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Introduced
    -0.80
    BuyableInstoreAndOnline
    -0.75
    ashtra
    -0.71
    portation
    -0.70
    marine
    -0.68
    fleet
    -0.64
    orbit
    -0.63
    heart
    -0.63
    prem
    -0.63
    Fle
    -0.62
    POSITIVE LOGITS
     purposes
    1.23
     example
    1.21
    bidden
    1.20
     instance
    1.13
    geries
    1.13
     awhile
    1.12
     reasons
    1.11
    gotten
    1.10
     centuries
    1.01
     sake
    0.98
    Act Density 0.265%

    No Known Activations