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

    Neuronpedia

    INDEX
    Explanations

    significant numerical values and terms related to measurements or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gate
    -0.19
     Gate
    -0.18
    :
    -0.16
    ↵
    -0.16
    3
    -0.15
    -0.15
    792
    -0.15
     Stadium
    -0.15
    6
    -0.15
     gates
    -0.15
    POSITIVE LOGITS
    islav
    0.17
    DeltaTime
    0.17
    YLON
    0.17
     RoundedRectangle
    0.15
    SSIP
    0.15
    íĥģ
    0.15
    adol
    0.14
    ahan
    0.14
    аÑĢам
    0.14
    _barrier
    0.14
    Act Density 0.005%

    No Known Activations