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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omens
    -0.17
    orf
    -0.15
    олом
    -0.14
     maduras
    -0.14
    akers
    -0.14
    ymb
    -0.14
    abcdefghijkl
    -0.14
    igan
    -0.14
    alli
    -0.13
     kav
    -0.13
    POSITIVE LOGITS
     passe
    0.16
    worthy
    0.15
     Kang
    0.14
    ľ
    0.14
     steals
    0.13
    elden
    0.13
    CoreApplication
    0.13
    erox
    0.13
     Bible
    0.13
    ellite
    0.13
    Act Density 0.197%

    No Known Activations