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

    Neuronpedia

    INDEX
    Explanations

    references to television shows and their ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resco
    -0.18
    openh
    -0.17
    sov
    -0.16
    VED
    -0.15
    esus
    -0.15
    vang
    -0.14
    unma
    -0.14
    tiler
    -0.14
     Wid
    -0.14
     Liber
    -0.14
    POSITIVE LOGITS
     Nickel
    0.22
     Adoles
    0.19
     tween
    0.19
     Disney
    0.18
    Teen
    0.17
     Jonas
    0.17
     teen
    0.17
     Teen
    0.16
     Tween
    0.16
     wholesome
    0.16
    Act Density 0.181%

    No Known Activations