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

    Neuronpedia

    INDEX
    Explanations

    numeric variables and their relationships within mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.89
    ]<<
    -0.73
    )$/,
    -0.69
    ]++;
    -0.69
    ]+=
    -0.69
    )|^{
    -0.69
    }}_{
    -0.66
    )}_{
    -0.65
    )++;
    -0.65
    ]='\
    -0.62
    POSITIVE LOGITS
     aDecoder
    0.69
    NOPQRST
    0.68
    0.65
    borderSide
    0.63
    UserScript
    0.63
    AddTagHelper
    0.61
    Jereo
    0.60
     Gaulle
    0.59
    tanleria
    0.59
    gdx
    0.58
    Act Density 0.391%

    No Known Activations