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

    Neuronpedia

    INDEX
    Explanations

    words related to disassembly or destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹ĥà¸Ī
    -0.16
    mars
    -0.16
    ди
    -0.15
     Haz
    -0.15
    enberg
    -0.15
    toFixed
    -0.14
    kip
    -0.14
    edy
    -0.13
    quam
    -0.13
    Ñĥн
    -0.13
    POSITIVE LOGITS
    orz
    0.15
     Height
    0.14
    ROUTE
    0.14
    ùi
    0.14
    ura
    0.14
    ts
    0.14
     Donne
    0.14
    Height
    0.14
    ordum
    0.14
    ods
    0.13
    Act Density 0.094%

    No Known Activations