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

    Neuronpedia

    INDEX
    Explanations

    phrases describing something as a significant or pronounced example of a certain attribute

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use "a" or "an" prominently, often indicating a subjective or informal description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTV
    -0.84
    psons
    -0.83
    ultimate
    -0.79
    achus
    -0.73
    eto
    -0.71
    aris
    -0.71
    ysc
    -0.70
    pta
    -0.68
    iless
    -0.68
     sorts
    -0.67
    POSITIVE LOGITS
     deterrent
    0.99
     tease
    0.90
     joke
    0.88
     contradiction
    0.84
     headache
    0.84
     nuisance
    0.81
     coincidence
    0.80
     setback
    0.79
     blocker
    0.79
     buffer
    0.78
    Act Density 0.084%

    No Known Activations