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

    Neuronpedia

    INDEX
    Explanations

    the presence of legal terminology and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     później
    -0.47
     (
    -0.45
     my
    -0.41
    smiles
    -0.41
     a
    -0.39
     an
    -0.38
    DOCTYPE
    -0.38
    '
    -0.37
    ↵
    -0.35
    м
    -0.35
    POSITIVE LOGITS
     tranſ
    0.85
     Diſ
    0.83
    ſelf
    0.82
     pleaſure
    0.82
     ſen
    0.81
     purpoſe
    0.79
     paſſ
    0.78
     ſeveral
    0.76
     houſe
    0.76
     Reſ
    0.76
    Act Density 1.612%

    No Known Activations