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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate opposition or resistance to specific legislation or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prung
    -0.17
    arkin
    -0.16
    cala
    -0.16
    éĿ©
    -0.15
    oyer
    -0.14
    eyn
    -0.14
    olem
    -0.14
     enumerable
    -0.14
    cer
    -0.14
     nec
    -0.13
    POSITIVE LOGITS
     Bowen
    0.17
    ÏĦαι
    0.16
    idi
    0.15
    angep
    0.14
    endencies
    0.14
    hazi
    0.14
    зÑĮ
    0.14
    δει
    0.14
    ange
    0.14
    .subplots
    0.14
    Act Density 0.446%

    No Known Activations