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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and studies related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äįást
    -0.16
     blat
    -0.15
     обла
    -0.15
    ylene
    -0.14
     actionTypes
    -0.14
    alloc
    -0.13
    onders
    -0.13
     (č↵
    -0.13
     batt
    -0.13
    .scalablytyped
    -0.13
    POSITIVE LOGITS
     only
    0.19
     altogether
    0.18
     Only
    0.18
     overall
    0.17
     Rough
    0.16
    0.16
     total
    0.15
    Only
    0.15
     Overall
    0.15
    rough
    0.15
    Act Density 0.142%

    No Known Activations