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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, especially the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LayoutStyle
    -0.49
    :
    -0.48
     springfox
    -0.47
    gdx
    -0.46
     Walkover
    -0.44
    win
    -0.44
     lunettes
    -0.44
    aarrggbb
    -0.44
    GetAxis
    -0.43
    ImageField
    -0.43
    POSITIVE LOGITS
    何より
    0.81
     velkommen
    0.79
     kasarigan
    0.79
    Portály
    0.77
    الحياه
    0.73
     hâte
    0.71
     natürlich
    0.69
     ofc
    0.69
     dispozici
    0.67
     للمعارف
    0.67
    Act Density 0.183%

    No Known Activations