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

    Neuronpedia

    INDEX
    Explanations

    concepts and discussions surrounding free speech and its implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hek
    -0.17
    lo
    -0.15
     exclusion
    -0.15
     blot
    -0.14
    led
    -0.14
     reject
    -0.14
    laus
    -0.14
     اجر
    -0.14
    à¹Ĥม
    -0.14
     homes
    -0.13
    POSITIVE LOGITS
    apgolly
    0.15
    ाधन
    0.15
    .DataVisualization
    0.15
    翼
    0.14
    ucch
    0.14
    amerate
    0.14
    GameOver
    0.14
    ktop
    0.14
    ALS
    0.14
    actus
    0.14
    Act Density 0.036%

    No Known Activations