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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and consequences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.92
     '\\;'
    -0.77
     ویکی‌پدیای
    -0.72
     дописавши
    -0.70
     betale
    -0.69
    новниш
    -0.69
    EndProject
    -0.66
    IsMutable
    -0.65
     onlyOwner
    -0.65
     utafitiHapana
    -0.65
    POSITIVE LOGITS
     or
    0.66
    /
    0.59
    或
    0.58
    又は
    0.54
    乃至
    0.52
    または
    0.51
    甚至
    0.50
     Quanto
    0.49
     alebo
    0.49
     nebo
    0.48
    Act Density 0.463%

    No Known Activations