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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods and processes

    oai_token-act-pair · gpt-3.5-turbo

    references to various methods or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gloom
    -0.59
     earnest
    -0.59
     impression
    -0.58
     Commodore
    -0.57
     Aliens
    -0.57
     pac
    -0.57
     Tyrann
    -0.56
     Sons
    -0.55
     Falcons
    -0.55
     Oval
    -0.55
    POSITIVE LOGITS
    ologies
    1.90
    ologically
    1.48
    ologic
    1.40
    ology
    1.30
    ical
    1.24
    ological
    1.21
    ologists
    1.12
    OLOGY
    1.10
    ologist
    1.07
    ically
    1.06
    Act Density 0.030%

    No Known Activations