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

    Neuronpedia

    INDEX
    Explanations

    statements starting with "If" and related to potential future outcomes

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements related to potential future events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \">
    -0.70
    Afee
    -0.68
    LESS
    -0.65
    ighters
    -0.64
    Interstitial
    -0.63
    ciating
    -0.62
    cial
    -0.59
    "></
    -0.59
     cu
    -0.59
    ITED
    -0.57
    POSITIVE LOGITS
     someday
    1.14
     tomorrow
    1.09
     hereafter
    0.95
     2022
    0.82
     2019
    0.75
     anytime
    0.73
     succeeds
    0.72
     succeed
    0.71
     2025
    0.71
     2020
    0.70
    Act Density 0.443%

    No Known Activations