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

    Neuronpedia

    INDEX
    Explanations

    elements related to movie reviews and production credits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndo
    -0.15
    (strict
    -0.15
    ëıĻìķĪ
    -0.14
     Sas
    -0.14
     Pron
    -0.14
    '=>"
    -0.14
     tpl
    -0.14
     brittle
    -0.14
    idf
    -0.13
    anders
    -0.13
    POSITIVE LOGITS
     Fast
    0.27
    Fast
    0.26
     Furious
    0.25
     FAST
    0.24
     fast
    0.24
    fast
    0.23
     Vin
    0.22
    -fast
    0.21
    FAST
    0.20
     Diesel
    0.20
    Act Density 0.015%

    No Known Activations