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

    Neuronpedia

    INDEX
    Explanations

    references to societal structures and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schäfer
    -0.47
    contrar
    -0.45
    occuper
    -0.44
     material
    -0.43
    pão
    -0.43
     bestaande
    -0.42
     zaś
    -0.41
     moral
    -0.41
    transQ
    -0.41
    moral
    -0.40
    POSITIVE LOGITS
     similar
    0.65
     Similar
    0.58
    Similar
    0.57
     similares
    0.56
    similar
    0.56
    RenderAtEndOf
    0.53
     comparable
    0.52
     akin
    0.52
     ähnliche
    0.50
     схо
    0.48
    Act Density 0.617%

    No Known Activations