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

    Neuronpedia

    INDEX
    Explanations

    mentions of probability or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to probability or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.84
    Interstitial
    -0.83
    uala
    -0.77
     Flavoring
    -0.71
    asus
    -0.71
    artney
    -0.70
    VK
    -0.69
    Application
    -0.68
    export
    -0.68
    System
    -0.68
    POSITIVE LOGITS
     odds
    1.28
     collide
    0.79
     ratio
    0.78
     sum
    0.74
     athlet
    0.71
     tack
    0.70
     peg
    0.70
     irresist
    0.69
     worsh
    0.69
     belie
    0.68
    Act Density 0.012%

    No Known Activations