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

    Neuronpedia

    INDEX
    Explanations

    political and social issues related to LGBTQ+ rights and corruption, particularly focusing on transgender issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢº
    -0.77
    ahime
    -0.75
    earchers
    -0.72
    sg
    -0.70
     Offline
    -0.70
     NX
    -0.67
    undrum
    -0.66
    iple
    -0.65
    oug
    -0.65
    raft
    -0.65
    POSITIVE LOGITS
     supposedly
    1.07
     blatantly
    0.91
     theirs
    0.88
     conveniently
    0.88
     incidentally
    0.87
     purportedly
    0.87
     duly
    0.86
     ostensibly
    0.84
     goddamn
    0.83
     disav
    0.82
    Act Density 0.943%

    No Known Activations