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

    Neuronpedia

    INDEX
    Explanations

    references to historical films and their themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mand
    -0.16
    467
    -0.15
     bang
    -0.14
    engin
    -0.14
    決
    -0.14
    oi
    -0.14
    deck
    -0.14
    Oak
    -0.13
    mand
    -0.13
    ieee
    -0.13
    POSITIVE LOGITS
     wet
    0.21
     Wet
    0.21
     ta
    0.20
     kun
    0.17
     fil
    0.16
     Ta
    0.15
     kern
    0.15
     nao
    0.15
     hers
    0.15
    ombres
    0.15
    Act Density 0.071%

    No Known Activations