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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal emotions and thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.94
    Espèce
    -0.84
    IsMutable
    -0.77
    يكب
    -0.73
    Vidite
    -0.71
     pinulongan
    -0.68
    opsida
    -0.68
     Paglinawan
    -0.68
    SuppressMessage
    -0.68
     GetEnumerator
    -0.67
    POSITIVE LOGITS
     ведь
    0.68
    だって
    0.64
     certainly
    0.60
     even
    0.58
    certainly
    0.51
    ünkü
    0.50
     anzi
    0.49
    甚至
    0.48
    even
    0.48
     اینکه
    0.47
    Act Density 0.254%

    No Known Activations