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

    Neuronpedia

    INDEX
    Explanations

    groups or group-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Latest
    -0.72
    LV
    -0.71
    Adv
    -0.70
    zzy
    -0.65
    SIGN
    -0.64
    shire
    -0.63
    lvl
    -0.63
     Appears
    -0.63
    DAY
    -0.62
     DEC
    -0.62
    POSITIVE LOGITS
    roups
    1.02
    arettes
    0.94
    ativity
    0.90
     affili
    0.87
    emonium
    0.85
    groups
    0.81
    anguage
    0.81
    arette
    0.80
    imore
    0.79
    ings
    0.79
    Act Density 0.044%

    No Known Activations