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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wald
    -0.15
    worm
    -0.15
    برÛĮ
    -0.14
    orient
    -0.14
    aws
    -0.14
    ously
    -0.14
    roi
    -0.14
    ago
    -0.14
    hell
    -0.14
    cap
    -0.13
    POSITIVE LOGITS
    VERRIDE
    0.17
    大人
    0.16
    imson
    0.15
     Leban
    0.15
    estre
    0.15
     ustanov
    0.14
    GetInt
    0.14
    rnek
    0.14
    lendir
    0.14
    -called
    0.14
    Act Density 0.009%

    No Known Activations