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

    Neuronpedia

    INDEX
    Explanations

    instances of specific names or identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anou
    -0.14
    transfer
    -0.14
     Samar
    -0.13
    akan
    -0.13
    EMA
    -0.13
    tp
    -0.13
    анÑĮ
    -0.13
    óz
    -0.13
    ëĸ
    -0.13
    disk
    -0.13
    POSITIVE LOGITS
    uras
    0.15
    erville
    0.14
     célib
    0.14
    ansa
    0.14
     yes
    0.14
    eyse
    0.13
    okud
    0.13
     Fluid
    0.13
    ansi
    0.13
    пов
    0.13
    Act Density 0.105%

    No Known Activations