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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbs that describe actions and states in a detailed manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},
    -0.75
    "],
    -0.72
    '].'
    -0.72
    }`).
    -0.70
    StoryboardSegue
    -0.69
    "]));
    -0.67
    ")));
    -0.65
    "])
    -0.65
    "]
    -0.63
    '">
    -0.63
    POSITIVE LOGITS
     without
    0.70
    ly
    0.67
     רבה
    0.63
     تعدى
    0.62
     demais
    0.61
     enough
    0.61
     during
    0.61
     with
    0.60
    uttosto
    0.59
     indeed
    0.59
    Act Density 0.440%

    No Known Activations