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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .called
    -0.15
     USING
    -0.14
     nawet
    -0.14
    åį´
    -0.13
    getSingleton
    -0.13
    ():↵↵
    -0.13
    .exist
    -0.12
    ":↵↵
    -0.12
    ':↵↵
    -0.12
     lẫn
    -0.12
    POSITIVE LOGITS
     used
    0.32
     for
    0.25
     to
    0.25
     representing
    0.24
     that
    0.23
    used
    0.23
     Used
    0.22
    çĶ¨äºİ
    0.22
     describing
    0.22
     which
    0.21
    Act Density 0.088%

    No Known Activations