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

    Neuronpedia

    INDEX
    Explanations

    technical terms and measurements related to energy, resistance, and signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seç
    -0.17
    addle
    -0.16
    aw
    -0.15
    ay
    -0.15
    anning
    -0.15
    isco
    -0.15
     toto
    -0.14
     Newman
    -0.14
    ssel
    -0.14
    ango
    -0.14
    POSITIVE LOGITS
     generated
    0.26
     produced
    0.24
     Produced
    0.23
     Generated
    0.23
    Generated
    0.22
    generated
    0.21
     GENERATED
    0.21
     generation
    0.21
    -output
    0.19
    generation
    0.19
    Act Density 0.178%

    No Known Activations