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

    Neuronpedia

    INDEX
    Explanations

    statements related to behavioral effects and influences, particularly concerning children and media consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     people
    -0.69
     everyone
    -0.67
     ppl
    -0.66
     everybody
    -0.66
     Obrador
    -0.65
    people
    -0.64
     players
    -0.63
     लोगों
    -0.62
     folks
    -0.62
    お客様
    -0.61
    POSITIVE LOGITS
     themselves
    1.60
     their
    1.35
    themselves
    1.27
    their
    1.11
    Their
    1.07
     Their
    0.92
     الرياضيه
    0.84
     ihres
    0.84
     ihrem
    0.84
     ihren
    0.83
    Act Density 0.930%

    No Known Activations