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

    Neuronpedia

    INDEX
    Explanations

    concepts related to self-awareness and interconnectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    337
    -0.17
     Zucker
    -0.15
    iew
    -0.15
    egg
    -0.14
    igen
    -0.14
     Heller
    -0.14
    834
    -0.14
    igs
    -0.14
    inde
    -0.14
    336
    -0.14
    POSITIVE LOGITS
     Krish
    0.21
     Conditioning
    0.17
    ayo
    0.17
     Brock
    0.15
     flowering
    0.15
     Ved
    0.15
    飯
    0.15
    abra
    0.15
     Educational
    0.15
     sir
    0.14
    Act Density 0.006%

    No Known Activations