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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols related to equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mxArray
    -0.77
    lą
    -0.67
    ్
    -0.64
     ครับ
    -0.64
    ︎
    -0.63
     endblock
    -0.62
    s
    -0.62
    _()
    -0.62
    ware
    -0.61
    [toxicity=0]
    -0.60
    POSITIVE LOGITS
    ########.
    0.95
    |}{$
    0.87
    konomi
    0.82
     $_(
    0.81
    + 
    0.80
    expandindo
    0.80
    силь
    0.77
     Rosal
    0.76
     上午
    0.74
     Gretchen
    0.72
    Act Density 0.249%

    No Known Activations