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

    Neuronpedia

    INDEX
    Explanations

    rules and restrictions regarding park behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verted
    -0.15
    è¿«
    -0.15
    enen
    -0.14
     VARIABLES
    -0.14
    erce
    -0.14
    iro
    -0.13
    asaki
    -0.13
    lov
    -0.13
    owied
    -0.13
    moth
    -0.13
    POSITIVE LOGITS
     Smoking
    0.21
     smoking
    0.21
     noise
    0.20
     disruptive
    0.20
     pets
    0.17
     misuse
    0.17
     gum
    0.17
     chewing
    0.17
     unauthorized
    0.17
     Noise
    0.17
    Act Density 0.055%

    No Known Activations