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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming concepts and functionality in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raya
    -0.16
    anner
    -0.16
    ober
    -0.15
    rita
    -0.14
     Beck
    -0.13
    /../
    -0.13
    aves
    -0.13
     ÑĤем
    -0.13
    طبÙĬ
    -0.13
     Rit
    -0.13
    POSITIVE LOGITS
    argon
    0.18
    esti
    0.15
    regist
    0.15
    agoon
    0.14
    achs
    0.14
    ĥĿ
    0.13
    ALI
    0.13
    RCT
    0.13
    781
    0.13
    235
    0.13
    Act Density 0.521%

    No Known Activations