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

    Neuronpedia

    INDEX
    Explanations

    specific key terms and names related to titles and character roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ereo
    -0.16
    ÑĪев
    -0.14
     pj
    -0.14
    erland
    -0.14
    fty
    -0.14
     Fist
    -0.14
    éĹ
    -0.14
    151
    -0.14
    eldon
    -0.13
     frac
    -0.13
    POSITIVE LOGITS
     Dexter
    0.42
     Dex
    0.30
     Deb
    0.29
     Miami
    0.27
    Miami
    0.25
     Harrison
    0.24
    DEX
    0.23
    exter
    0.23
     Trinity
    0.23
     dex
    0.22
    Act Density 0.002%

    No Known Activations