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

    Neuronpedia

    INDEX
    Explanations

    direct quotations or references from interview articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unner
    -0.15
    adal
    -0.15
    hape
    -0.14
    ennen
    -0.14
    infra
    -0.14
    Īĺ
    -0.14
    odyn
    -0.13
    ļĮ
    -0.13
    .IsEnabled
    -0.13
    ždy
    -0.13
    POSITIVE LOGITS
     Pitch
    0.28
    Pitch
    0.27
    pitch
    0.24
     Noise
    0.23
     Spin
    0.23
    Noise
    0.23
    Spin
    0.21
     Ster
    0.21
     Rolling
    0.20
     Spinner
    0.20
    Act Density 0.109%

    No Known Activations