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

    Neuronpedia

    INDEX
    Explanations

    instances of the keyword "new" related to object creation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilde
    -0.18
    ittel
    -0.17
    .XR
    -0.15
    ä¸ĺ
    -0.15
    ugal
    -0.14
    hk
    -0.14
     èĬ
    -0.14
    ado
    -0.14
    SCO
    -0.13
    mek
    -0.13
    POSITIVE LOGITS
    utex
    0.15
     states
    0.15
    623
    0.14
    grav
    0.14
     Bradley
    0.14
    controls
    0.14
    icers
    0.13
     dend
    0.13
     bypass
    0.13
     Sno
    0.13
    Act Density 0.012%

    No Known Activations