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

    Neuronpedia

    INDEX
    Explanations

    phrases or statements confirming the truthfulness of a claim or fact

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "true" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uty
    -0.75
    adish
    -0.74
    ocene
    -0.72
    ILE
    -0.70
    ambo
    -0.69
    ourning
    -0.68
     Sections
    -0.68
    uled
    -0.67
     booths
    -0.67
    chains
    -0.67
    POSITIVE LOGITS
     true
    0.88
    true
    0.86
    quickShipAvailable
    0.80
    True
    0.77
     believers
    0.76
     TRUE
    0.76
    blooded
    0.72
     believer
    0.72
     è£ıè¦ļéĨĴ
    0.69
    ance
    0.68
    Act Density 0.017%

    No Known Activations