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

    Neuronpedia

    INDEX
    Explanations

    political and governmental terms related to power and control

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -0.71
     upvoted
    -0.63
     disagre
    -0.61
     naï
    -0.61
     fucker
    -0.59
    <bos>
    -0.59
     cuck
    -0.58
     blushed
    -0.57
     ineffec
    -0.57
     motherfucker
    -0.56
    POSITIVE LOGITS
     autunno
    0.73
     virtù
    0.70
     regardant
    0.66
     Amérique
    0.66
     abbra
    0.66
     appuy
    0.65
     écout
    0.65
     onore
    0.62
     Ngb
    0.62
     considération
    0.62
    Act Density 0.472%

    No Known Activations