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

    Neuronpedia

    INDEX
    Explanations

    exclamations and punctuation symbols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.75
     scatter
    -0.73
     Libyan
    -0.68
     DPR
    -0.67
     purse
    -0.64
    enegger
    -0.63
     Afric
    -0.63
     Tid
    -0.63
     lodging
    -0.62
     shroud
    -0.61
    POSITIVE LOGITS
    ¹
    1.33
    º
    1.31
    £
    1.23
    į
    1.21
    Į
    1.18
    Ĵ
    1.17
    ı
    1.16
    §
    1.15
    ¬
    1.14
    »
    1.11
    Act Density 1.275%

    No Known Activations