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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osterone
    -0.70
    ãħĭ
    -0.70
    itled
    -0.69
    buster
    -0.68
    ivas
    -0.67
    bard
    -0.65
    thal
    -0.64
    heimer
    -0.64
    riger
    -0.64
    ppa
    -0.64
    POSITIVE LOGITS
     virtue
    1.18
    products
    1.02
     multiplying
    0.91
     means
    0.80
     passers
    0.80
     leaps
    0.76
     subtract
    0.76
     invoking
    0.76
     accident
    0.76
     combining
    0.75
    Act Density 0.086%

    No Known Activations