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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong interest or enthusiasm towards certain topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.94
    eor
    -0.83
    ãĥĥãĥī
    -0.75
    rooms
    -0.74
     Sachs
    -0.70
    å¸
    -0.70
    ãĤ¤ãĥĪ
    -0.64
    avis
    -0.63
    ãĥİ
    -0.60
    äºĶ
    -0.60
    POSITIVE LOGITS
     passionately
    1.01
    atical
    0.99
     passion
    0.94
    ately
    0.86
    uous
    0.86
    ful
    0.84
    uality
    0.83
    acy
    0.83
    itiveness
    0.80
     passions
    0.80
    Act Density 0.033%

    No Known Activations