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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "added," particularly in contexts of reporting statements or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pri
    -0.47
     or
    -0.44
    ++;
    -0.44
    ".$_
    -0.44
     [];
    -0.43
    laß
    -0.43
    cnica
    -0.43
     Big
    -0.42
     D
    -0.42
     I
    -0.42
    POSITIVE LOGITS
    complexContent
    0.97
    awtextra
    0.91
     propOrder
    0.91
    وأضاف
    0.87
     esternos
    0.85
    GOTREF
    0.85
    abestanden
    0.83
     noqa
    0.82
     itſelf
    0.82
     дописавши
    0.80
    Act Density 0.050%

    No Known Activations