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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "of" indicating relationships or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rss
    -0.79
    soon
    -0.78
    ãģ®éŃĶ
    -0.77
    rir
    -0.76
    >>\
    -0.75
    20439
    -0.75
    fur
    -0.74
    SPONSORED
    -0.74
    CIA
    -0.73
    Its
    -0.72
    POSITIVE LOGITS
     these
    1.31
     this
    1.00
     detecting
    0.91
     assigning
    0.90
     interpreting
    0.89
     determining
    0.88
     differences
    0.87
    these
    0.82
     such
    0.82
     modifying
    0.80
    Act Density 0.563%

    No Known Activations