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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal enjoyment or dislike towards characters and their development in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.77
    TagMode
    -0.67
     متعلقه
    -0.62
     [{
    -0.61
    paio
    -0.60
    sizeCache
    -0.60
     विश्वसनीयता
    -0.60
     Shakspeare
    -0.59
    ſelf
    -0.58
    المناصب
    -0.58
    POSITIVE LOGITS
     dislike
    0.63
     love
    0.60
     StatefulWidget
    0.58
     disliked
    0.56
     loved
    0.55
     loves
    0.51
    dislike
    0.50
     Love
    0.50
     dislikes
    0.49
    Anhalt
    0.49
    Act Density 0.285%

    No Known Activations