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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly Swedish figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    føring
    -0.68
     tjen
    -0.66
     måte
    -0.64
     ferdig
    -0.60
     seier
    -0.60
     samfun
    -0.59
     velg
    -0.58
    ført
    -0.58
     aktivitet
    -0.57
     køb
    -0.57
    POSITIVE LOGITS
     Sweden
    0.92
     Swedish
    0.90
     Uppsala
    0.86
    andinavia
    0.84
    skjaer
    0.83
    Sweden
    0.82
     Scandinavia
    0.79
    kegaard
    0.79
     swedish
    0.79
    Swedish
    0.79
    Act Density 0.424%

    No Known Activations