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

    Neuronpedia

    INDEX
    Explanations

    negative portrayals of societal issues and individual dysfunction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lig
    -0.18
    anness
    -0.15
     Lyon
    -0.14
    hots
    -0.14
    ActionButton
    -0.14
     Rogue
    -0.13
    884
    -0.13
     girls
    -0.13
    _RAD
    -0.13
     Femme
    -0.13
    POSITIVE LOGITS
    以为
    0.15
    ERY
    0.15
    estation
    0.14
    buz
    0.14
    ëį
    0.14
    UCKET
    0.14
    ayacak
    0.13
    ToOne
    0.13
     Ders
    0.13
    atinum
    0.13
    Act Density 0.279%

    No Known Activations