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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing upcoming events or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to projects or works in progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pring
    -0.66
    idious
    -0.60
    ename
    -0.56
     consent
    -0.56
     guiActiveUnfocused
    -0.56
     presence
    -0.54
     Protective
    -0.54
    istant
    -0.54
    lying
    -0.54
    ALD
    -0.54
    POSITIVE LOGITS
     showcases
    1.14
     celebrates
    1.11
     explores
    1.10
     focuses
    1.10
     combines
    1.08
     utilizes
    1.07
     specializes
    1.06
     incorporates
    1.04
     spans
    1.03
     revolves
    1.02
    Act Density 0.204%

    No Known Activations