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

    Neuronpedia

    INDEX
    Explanations

    references to political ideologies and socio-political promises within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardes
    -0.59
     né
    -0.51
    anal
    -0.46
     affects
    -0.45
    場合があります
    -0.43
     y
    -0.42
    тена
    -0.42
    のですか
    -0.42
     Mary
    -0.41
    estre
    -0.41
    POSITIVE LOGITS
    Hochspringen
    0.78
    SequentialGroup
    0.77
     myſelf
    0.73
     pleaſure
    0.72
     hoped
    0.71
     Theſe
    0.69
     $_"
    0.69
     Biôgrafia
    0.68
     raiſ
    0.67
     ſever
    0.65
    Act Density 0.408%

    No Known Activations