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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity or self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convertirse
    -0.54
     ň
    -0.51
     is
    -0.49
     the
    -0.46
    FieldNumber
    -0.46
    からです
    -0.46
     ích
    -0.45
     under
    -0.45
     CURLOPT
    -0.44
    blurRadius
    -0.43
    POSITIVE LOGITS
     myſelf
    0.94
     Мне
    0.88
     nakalista
    0.88
     Савезне
    0.84
     Estou
    0.84
    Мне
    0.82
     myself
    0.78
     meines
    0.75
     Saya
    0.75
     Нам
    0.74
    Act Density 0.527%

    No Known Activations