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

    Neuronpedia

    INDEX
    Explanations

    certain key adverbs and adjectives that convey strong emphasis or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.93
     ​​
    -0.91
    ים
    -0.83
     Ã
    -0.83
    letal
    -0.78
    urtstag
    -0.76
    RequestMapping
    -0.74
    yargs
    -0.74
    .$$
    -0.71
    _));
    -0.71
    POSITIVE LOGITS
    fix
    0.89
     Ellington
    0.86
     dressings
    0.85
     Bowles
    0.81
     ruines
    0.78
     blessé
    0.77
     condamné
    0.77
     Creature
    0.75
    Dior
    0.75
     Congregation
    0.74
    Act Density 0.201%

    No Known Activations