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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and emotional connections

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.66
    TagHelper
    -0.50
    Clik
    -0.48
    TProtocol
    -0.46
     Roskov
    -0.46
    https
    -0.45
     <=",
    -0.45
     вікі
    -0.44
    styleable
    -0.44
     however
    -0.43
    POSITIVE LOGITS
    Guaranteed
    0.67
    ]$}
    0.63
     guaranteed
    0.61
     automatisch
    0.61
     مشين
    0.60
    guar
    0.60
     Guaranteed
    0.60
    ]--;
    0.59
    HTH
    0.59
    Portale
    0.58
    Act Density 0.277%

    No Known Activations