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

    Neuronpedia

    INDEX
    Explanations

    declarative statements followed by the phrase "believe it or not"

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing conditional statements or expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocrat
    -0.62
    ipel
    -0.59
    edom
    -0.58
    iple
    -0.56
     ILCS
    -0.56
    ipation
    -0.56
    ENE
    -0.56
     antioxid
    -0.55
    legraph
    -0.55
    mitter
    -0.54
    POSITIVE LOGITS
    Else
    1.05
    chard
    0.91
    acular
    0.88
    acle
    0.87
    lando
    0.84
    acles
    0.81
     else
    0.78
    nery
    0.74
    ifice
    0.72
    nam
    0.72
    Act Density 0.077%

    No Known Activations