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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to concepts or situations of continual change or growth

    oai_token-act-pair · gpt-3.5-turbo

    the word "ever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.65
    RPG
    -0.65
     Beir
    -0.64
    é¾
    -0.64
    ItemTracker
    -0.64
    emia
    -0.64
    redients
    -0.61
     Anthem
    -0.61
     Tags
    -0.60
    pointers
    -0.60
    POSITIVE LOGITS
    green
    0.99
    lasting
    0.98
    more
    0.84
    THING
    0.84
     dreamed
    0.80
    theless
    0.79
    thing
    0.77
     onward
    0.71
    den
    0.68
     imagined
    0.66
    Act Density 0.022%

    No Known Activations