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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -1.15
     impelled
    -1.08
     endeavouring
    -1.06
     unwarran
    -1.04
     vainly
    -1.00
     disagre
    -1.00
     tolerably
    -1.00
     indescri
    -0.99
     unavoid
    -0.98
     impra
    -0.93
    POSITIVE LOGITS
     alkoh
    1.21
     kosme
    1.21
     silikon
    1.16
     ideolog
    1.11
     panik
    1.07
     solidar
    1.07
     anse
    1.06
     kooper
    1.04
     akus
    1.04
     praktik
    1.03
    Act Density 0.084%

    No Known Activations