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

    Neuronpedia

    INDEX
    Explanations

    terms related to achieving significant outcomes or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лек
    -0.16
     jenter
    -0.16
    ovo
    -0.15
    룡
    -0.15
    zdy
    -0.15
    hton
    -0.15
    .AI
    -0.14
    PasswordEncoder
    -0.14
    stk
    -0.14
    ónico
    -0.14
    POSITIVE LOGITS
    Ãłnh
    0.16
    rax
    0.15
    uzzle
    0.14
     Compensation
    0.13
    /results
    0.13
    ResultsController
    0.13
    eil
    0.13
     Coul
    0.13
     compensation
    0.13
    enth
    0.13
    Act Density 0.026%

    No Known Activations