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

    Neuronpedia

    INDEX
    Explanations

    references to literary achievements and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     records
    -0.15
    缤
    -0.14
     karÄ±ÅŁ
    -0.14
    ernote
    -0.14
    aea
    -0.14
    emand
    -0.13
    amma
    -0.13
     Hayward
    -0.13
     Folk
    -0.13
     Records
    -0.13
    POSITIVE LOGITS
    writing
    0.21
     Writers
    0.21
    WR
    0.19
     writing
    0.19
    -writing
    0.18
     NSK
    0.18
    -NLS
    0.18
     Writing
    0.17
     prose
    0.17
     Writer
    0.17
    Act Density 0.616%

    No Known Activations