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

    Neuronpedia

    INDEX
    Explanations

    the number zero

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "zero" and its various uses in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.87
    areth
    -0.75
    icken
    -0.75
    lov
    -0.74
    Interstitial
    -0.74
    akov
    -0.73
    RAW
    -0.71
    rough
    -0.70
    aukee
    -0.70
    gary
    -0.69
    POSITIVE LOGITS
     Hedge
    0.88
     Escape
    0.78
     percent
    0.78
     zero
    0.76
     amount
    0.75
     tolerance
    0.74
    hole
    0.74
    zero
    0.74
    ishly
    0.74
     sum
    0.72
    Act Density 0.019%

    No Known Activations