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

    Neuronpedia

    INDEX
    Explanations

    instances of humor or light-hearted communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    леж
    -0.16
    executable
    -0.15
    oogle
    -0.14
     Conserv
    -0.14
     Frank
    -0.14
     frank
    -0.14
     forb
    -0.14
    laps
    -0.14
    Frank
    -0.13
     Cruc
    -0.13
    POSITIVE LOGITS
    Seriously
    0.26
     Seriously
    0.23
     seriously
    0.23
     kidding
    0.23
     actually
    0.19
    Actually
    0.19
     Actually
    0.18
    actually
    0.17
     serious
    0.16
     cla
    0.15
    Act Density 0.077%

    No Known Activations