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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "shadow" with various levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to "Shadow" or related terms, particularly in a political or contextual setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickr
    -0.81
    ktop
    -0.73
    aii
    -0.71
    urses
    -0.70
    keye
    -0.70
    ilar
    -0.66
    ieves
    -0.64
     kHz
    -0.63
     Pwr
    -0.62
    urtles
    -0.62
    POSITIVE LOGITS
    boxing
    1.10
    loo
    1.06
    moon
    0.99
    fax
    0.93
    run
    0.87
    stats
    0.84
    runners
    0.84
    ners
    0.83
    lands
    0.79
     chancellor
    0.77
    Act Density 0.034%

    No Known Activations