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

    Neuronpedia

    INDEX
    Explanations

    phrasing that emphasizes certainty and affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Obrázky
    -0.85
    TagMode
    -0.67
    ="#"><
    -0.66
     htons
    -0.66
    forChild
    -0.64
     comigo
    -0.62
     vérit
    -0.62
     vertus
    -0.61
    eseorang
    -0.61
     дописавши
    -0.60
    POSITIVE LOGITS
     make
    1.01
    Make
    0.91
    make
    0.90
     MAKE
    0.88
     Make
    0.88
    Making
    0.80
     makes
    0.79
    MAKE
    0.79
     Making
    0.78
    MAKING
    0.76
    Act Density 0.116%

    No Known Activations