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

    Neuronpedia

    INDEX
    Explanations

    instances where something is described as being a good or beneficial thing

    oai_token-act-pair · gpt-3.5-turbo

    indefinite articles and the general concept of "something" or "one" as it relates to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agree
    -0.85
    Edit
    -0.80
     Izan
    -0.75
    Versions
    -0.72
    ontent
    -0.70
    Anim
    -0.67
    achu
    -0.67
    Attempts
    -0.66
    armor
    -0.64
     edits
    -0.64
    POSITIVE LOGITS
     nuisance
    1.00
     fruitful
    0.95
     lot
    0.92
     worthwhile
    0.91
    versive
    0.90
     boon
    0.88
     handy
    0.87
     cornerstone
    0.87
     huge
    0.86
     bit
    0.85
    Act Density 0.278%

    No Known Activations