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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governance and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anstatt
    -0.61
    而不是
    -0.59
    chmal
    -0.58
     perhaps
    -0.56
     tantôt
    -0.54
     apparently
    -0.53
     presumably
    -0.53
    tonsoft
    -0.52
     referenties
    -0.52
     aparentemente
    -0.51
    POSITIVE LOGITS
    EVER
    0.87
     anzi
    0.78
     nor
    0.77
    むしろ
    0.74
     متعلقه
    0.74
     EVER
    0.72
     Nor
    0.72
    unless
    0.71
    ύτε
    0.69
     بلکه
    0.66
    Act Density 0.229%

    No Known Activations