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

    Neuronpedia

    INDEX
    Explanations

    references to political situations or governmental statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     synagogue
    -0.80
    chini
    -0.79
    ivably
    -0.74
    slot
    -0.69
    aban
    -0.68
    rament
    -0.68
    raf
    -0.67
     FANTASY
    -0.66
     rather
    -0.66
    nikov
    -0.65
    POSITIVE LOGITS
    Interested
    0.69
    Thomas
    0.67
    Machine
    0.64
    Ass
    0.62
    SPONSORED
    0.62
    Cong
    0.60
    ENCY
    0.60
    arching
    0.60
    Speaking
    0.58
    Add
    0.58
    Act Density 0.231%

    No Known Activations