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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating commands or state changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kendrick
    -0.16
    ochen
    -0.15
    aida
    -0.15
    olest
    -0.15
    ξι
    -0.14
    anson
    -0.14
     caul
    -0.13
    ismic
    -0.13
    ragon
    -0.13
    lish
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.18
    à¥ĩà¤ľ
    0.15
     pace
    0.15
     Pace
    0.14
    urette
    0.14
    adel
    0.14
    ibble
    0.14
     ngang
    0.14
    ázev
    0.14
    оÑĤÑĭ
    0.14
    Act Density 0.008%

    No Known Activations