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

    Neuronpedia

    INDEX
    Explanations

    descriptors that emphasize exceptional qualities or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sortie
    -0.51
    ownik
    -0.49
     umum
    -0.48
     tertentu
    -0.46
    そろそろ
    -0.46
     agak
    -0.45
     nieco
    -0.45
    有一定的
    -0.44
     <=",
    -0.44
    G
    -0.44
    POSITIVE LOGITS
     amounts
    1.02
     feats
    0.98
     Amounts
    0.93
     للمعارف
    0.91
     🤩
    0.90
    кновен
    0.90
    amounts
    0.88
    gggg
    0.88
     amount
    0.87
    SuccessListener
    0.84
    Act Density 0.147%

    No Known Activations