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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Watch" indicating recommendations or prompts to view content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IMO
    -0.15
    .bunifuFlatButton
    -0.15
    ãģĸ
    -0.14
    .scrollTo
    -0.14
     rig
    -0.14
    ilo
    -0.14
    že
    -0.13
    StackNavigator
    -0.13
     Extras
    -0.13
    帯
    -0.13
    POSITIVE LOGITS
    LOAT
    0.17
    edor
    0.17
    ivas
    0.16
    lesh
    0.16
    /html
    0.15
    edException
    0.15
    ington
    0.15
    letal
    0.15
    itan
    0.14
     Princip
    0.14
    Act Density 0.016%

    No Known Activations