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

    Neuronpedia

    INDEX
    Explanations

    references to survey data and methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cur
    -0.17
    appa
    -0.17
     er
    -0.15
    าà¸
    -0.14
    pta
    -0.14
     wear
    -0.13
     bene
    -0.13
     palm
    -0.13
     Cur
    -0.13
     foreign
    -0.13
    POSITIVE LOGITS
    elman
    0.17
    onde
    0.16
    BufferData
    0.15
    haul
    0.15
    /schema
    0.15
    екÑĤ
    0.14
     Collector
    0.14
    inal
    0.14
     data
    0.14
    .data
    0.14
    Act Density 0.013%

    No Known Activations