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

    Neuronpedia

    INDEX
    Explanations

    words related to physical qualities or attributes such as agility, strength, accessibility, and shape

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal issues and human interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verbs
    -0.71
    icus
    -0.69
    Cell
    -0.65
     Versus
    -0.65
    cius
    -0.63
    alus
    -0.63
    zan
    -0.63
    Zen
    -0.62
    Js
    -0.62
    renheit
    -0.61
    POSITIVE LOGITS
     thereof
    0.86
     portion
    0.85
     aspects
    0.84
     portions
    0.80
     aspect
    0.78
     industries
    0.76
     respectively
    0.76
     sectors
    0.73
     alike
    0.71
     sections
    0.70
    Act Density 0.253%

    No Known Activations