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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional testing in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vey
    -0.16
    ynet
    -0.16
    arser
    -0.14
     Kral
    -0.14
    ANGO
    -0.14
    [assembly
    -0.14
    Thunk
    -0.14
     Souls
    -0.14
    MOOTH
    -0.14
    âĸį
    -0.13
    POSITIVE LOGITS
     bolt
    0.17
     bol
    0.14
    olley
    0.14
     correct
    0.14
    oldt
    0.13
    оби
    0.13
    abouts
    0.13
    Locker
    0.13
    Pocket
    0.13
    bolt
    0.13
    Act Density 0.015%

    No Known Activations