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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lists or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strap
    -0.15
     sag
    -0.14
    ä¼¼çļĦ
    -0.14
     h
    -0.14
     fr
    -0.13
    à¸ģà¸ķ
    -0.13
    atown
    -0.13
     Thrones
    -0.13
     Laugh
    -0.13
     dil
    -0.13
    POSITIVE LOGITS
    essel
    0.15
    ood
    0.15
    аÑĢан
    0.15
    ONGL
    0.15
     Lans
    0.14
    rome
    0.14
    ames
    0.14
    acements
    0.14
    rieve
    0.14
    ivery
    0.14
    Act Density 0.030%

    No Known Activations