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

    Neuronpedia

    INDEX
    Explanations

    symbols and icons associated with user interface elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.92
    Hochspringen
    -0.81
    "])
    -0.79
     ***!
    -0.74
     通販
    -0.72
     autorytatywna
    -0.72
     незавершена
    -0.71
    ThroughAttribute
    -0.69
    expandindo
    -0.69
    </caption>
    -0.69
    POSITIVE LOGITS
     kasarigan
    0.58
     InputDecoration
    0.54
    বা
    0.51
    kesan
    0.51
    i
    0.50
    -
    0.50
    يسة
    0.49
     DDS
    0.48
     staden
    0.48
    iid
    0.48
    Act Density 0.014%

    No Known Activations