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

    Neuronpedia

    INDEX
    Explanations

    quotes or speech marks indicating direct speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isContained
    -0.17
    ↵↵
    -0.17
    actionDate
    -0.17
    íĨłíĨł
    -0.15
    chwitz
    -0.15
    ìľłë¨¸
    -0.14
    yyvsp
    -0.14
    ë§ĮëĤ¨
    -0.14
    itr
    -0.14
     Geile
    -0.14
    POSITIVE LOGITS
    oner
    0.21
    abs
    0.20
    eer
    0.20
    amp
    0.20
    ext
    0.19
     abs
    0.19
     Abs
    0.18
    100
    0.18
    amic
    0.17
    99
    0.16
    Act Density 0.099%

    No Known Activations