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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to measurements, comparisons, and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fifth
    -0.23
     fifth
    -0.19
    äºĶæľĪ
    -0.19
    -May
    -0.16
    ertino
    -0.16
     Five
    -0.16
    rier
    -0.15
    ipple
    -0.15
    µ
    -0.15
    .scalablytyped
    -0.15
    POSITIVE LOGITS
    6
    0.28
    7
    0.25
     sixth
    0.25
     Sixth
    0.21
     six
    0.19
     seven
    0.18
     seventh
    0.18
     Seventh
    0.17
    ६
    0.16
    åħŃ
    0.16
    Act Density 0.095%

    No Known Activations