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

    Neuronpedia

    INDEX
    Explanations

    names and their variations or spellings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sled
    -0.15
    iddet
    -0.15
    odega
    -0.15
    iegel
    -0.14
    herits
    -0.14
    pike
    -0.14
    ilee
    -0.14
    geç
    -0.14
    pecia
    -0.14
    udic
    -0.14
    POSITIVE LOGITS
     Hannity
    0.21
     Lantern
    0.20
     Jennings
    0.19
     Lennon
    0.19
     lantern
    0.18
    URN
    0.17
    ern
    0.17
     Dün
    0.17
     Brennan
    0.17
     Reyn
    0.16
    Act Density 0.084%

    No Known Activations