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

    Neuronpedia

    INDEX
    Explanations

    code related to object and class manipulation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goldberg
    -0.15
    agna
    -0.14
     respectively
    -0.14
    outer
    -0.14
    AWN
    -0.13
    acin
    -0.13
    idon
    -0.13
     immunity
    -0.13
    duk
    -0.13
    488
    -0.12
    POSITIVE LOGITS
    Gatt
    0.16
    iye
    0.16
    uristic
    0.14
     prostitu
    0.14
    ̣
    0.14
    oline
    0.14
    alic
    0.14
    rita
    0.14
    éģ
    0.14
    оÑĢод
    0.14
    Act Density 0.030%

    No Known Activations