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

    Neuronpedia

    INDEX
    Explanations

    percentages or indicators of statistical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.59
     gepubliceerd
    -0.54
     Ähn
    -0.53
     StatefulWidget
    -0.51
    migrationBuilder
    -0.50
    illiard
    -0.50
     mineures
    -0.48
    Cheat
    -0.48
     often
    -0.48
    ος
    -0.47
    POSITIVE LOGITS
     completely
    1.04
     totally
    1.03
     Totally
    1.01
     sepenuhnya
    0.99
     Completely
    0.97
    Completely
    0.96
     pure
    0.93
     fully
    0.93
     entirely
    0.93
     COMPLE
    0.91
    Act Density 0.136%

    No Known Activations