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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structure in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eps
    -0.16
     Pent
    -0.15
    aris
    -0.15
    mann
    -0.15
    zo
    -0.14
    axter
    -0.14
    lif
    -0.14
    abile
    -0.14
    iland
    -0.13
    iek
    -0.13
    POSITIVE LOGITS
    ioni
    0.17
    ramid
    0.16
    ator
    0.14
    745
    0.14
    316
    0.14
    uze
    0.14
    ichten
    0.14
    907
    0.14
    SHIP
    0.13
    isify
    0.13
    Act Density 0.012%

    No Known Activations