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

    Neuronpedia

    INDEX
    Explanations

    information related to study design and methods in research

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.74
    GEBURTSDATUM
    -0.71
    ftagPool
    -0.67
    ]^
    -0.59
    ukone
    -0.58
     المتحدة
    -0.58
     فريبيس
    -0.57
    thington
    -0.57
    RegressionTest
    -0.54
    HttpPut
    -0.54
    POSITIVE LOGITS
     setae
    0.66
     Hanford
    0.65
     condam
    0.62
     gobernador
    0.59
     magique
    0.57
     termica
    0.57
     gminy
    0.55
     democrática
    0.54
     GOVERNOR
    0.53
     bidet
    0.53
    Act Density 0.017%

    No Known Activations