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

    Neuronpedia

    INDEX
    Explanations

    numbers and references to legal or judicial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unhofer
    -0.70
     Giz
    -0.70
    +#+
    -0.67
     Frick
    -0.64
    apropri
    -0.63
    期刊论文
    -0.62
     propter
    -0.61
    geral
    -0.61
    OGND
    -0.60
     externi
    -0.60
    POSITIVE LOGITS
     urbanas
    0.82
     titolata
    0.75
     volna
    0.73
    wanzig
    0.70
     françaises
    0.69
     tavolo
    0.69
     sottile
    0.69
     xmax
    0.68
    UnitTesting
    0.67
     Sabina
    0.65
    Act Density 0.660%

    No Known Activations