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

    Neuronpedia

    INDEX
    Explanations

    various forms of action and humor within film critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haus
    -0.17
    hus
    -0.15
     Kaynak
    -0.14
    га
    -0.14
    ãĤ¶ãĥ¼
    -0.14
    isis
    -0.13
    _globals
    -0.13
    estruct
    -0.13
    erable
    -0.13
    ãĥ³ãĤ¬
    -0.13
    POSITIVE LOGITS
    sek
    0.17
    anza
    0.17
    vy
    0.16
    aniel
    0.15
    dez
    0.15
     CascadeType
    0.14
     Sala
    0.14
    endar
    0.14
     Conserv
    0.13
    umann
    0.13
    Act Density 0.069%

    No Known Activations