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

    Neuronpedia

    INDEX
    Explanations

    instances of the contraction "don’t" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <h1>
    -0.53
    The
    -0.46
    <h2>
    -0.44
    ↵↵
    -0.39
    <h3>
    -0.39
    A
    -0.36
     étoit
    -0.35
    <h4>
    -0.35
    package
    -0.33
    from
    -0.32
    POSITIVE LOGITS
    ſicht
    1.02
     ddelwed
    1.00
     zwiſchen
    0.99
    linawan
    0.97
    ロウィン
    0.96
     imagui
    0.96
     deſſen
    0.96
    iſche
    0.93
    ſchaft
    0.93
     geſch
    0.93
    Act Density 3.359%

    No Known Activations