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

    Neuronpedia

    INDEX
    Explanations

    entities, variables, and method names commonly used in programming and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ODO
    -0.17
    atta
    -0.14
    rawer
    -0.14
     trai
    -0.14
    odo
    -0.13
    URRENCY
    -0.13
    ãĤ¤ãĤ¯
    -0.13
    andal
    -0.13
    sembler
    -0.13
     roÄįnÃŃ
    -0.13
    POSITIVE LOGITS
    vant
    0.15
    china
    0.14
    ichel
    0.14
    _ASSUME
    0.14
    ether
    0.13
    ubber
    0.13
    asti
    0.13
     Braun
    0.13
    uve
    0.13
    avenport
    0.13
    Act Density 0.003%

    No Known Activations