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

    Neuronpedia

    INDEX
    Explanations

    words related to providing assistance, strength, protection, comfort, support, confidence, talent, power, coverage, cheer, revenue, care, regulation, and success

    oai_token-act-pair · gpt-3.5-turbo

    terms related to support and positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otine
    -0.71
    ovie
    -0.66
     Mile
    -0.64
     Spartan
    -0.56
     Ric
    -0.56
     outing
    -0.55
    artment
    -0.55
     Estate
    -0.55
     affair
    -0.54
     invention
    -0.53
    POSITIVE LOGITS
    fully
    0.92
    ively
    0.83
    lessly
    0.79
    ifully
    0.78
    ably
    0.77
    arily
    0.77
    iless
    0.75
    ously
    0.73
    istically
    0.71
    ally
    0.70
    Act Density 0.334%

    No Known Activations