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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "said" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    `]
    -0.94
    bibfield
    -0.90
    ?>">
    -0.84
    bibinfo
    -0.83
    存于互联网档案馆
    -0.79
    ')")
    -0.78
     */
    -0.77
     nahilalakip
    -0.77
     Gera
    -0.76
    Gera
    -0.75
    POSITIVE LOGITS
     said
    1.63
    said
    1.47
     SAID
    1.40
    Said
    1.37
     Said
    1.35
     sayings
    1.29
    SAY
    1.23
     says
    1.21
     Says
    1.19
     Saying
    1.13
    Act Density 0.070%

    No Known Activations