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

    Neuronpedia

    INDEX
    Explanations

    instances of words that convey significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Esau
    -0.77
     Sodom
    -0.76
     zelve
    -0.74
    tagHelperRunner
    -0.74
     Athenians
    -0.74
     Fascism
    -0.73
     Philist
    -0.73
     Phry
    -0.72
     ciascuno
    -0.72
     Mahomet
    -0.72
    POSITIVE LOGITS
     same
    1.39
     entire
    1.16
     rest
    1.09
     latter
    1.07
     various
    1.04
     most
    1.03
     usual
    0.98
     final
    0.97
     vast
    0.97
     latest
    0.96
    Act Density 2.548%

    No Known Activations