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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is merely a representation or concept, rather than a concrete reality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate something is a trivial or minor issue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    successfully
    -0.77
    lees
    -0.76
    ornia
    -0.74
    2020
    -0.73
    cue
    -0.73
    inguished
    -0.72
    pora
    -0.71
     lest
    -0.70
     Notably
    -0.70
    Only
    -0.69
    POSITIVE LOGITS
     coincidence
    1.08
     placeholder
    1.03
     decoration
    0.91
     curiosity
    0.86
     footnote
    0.86
     fig
    0.85
     plain
    0.85
     nuisance
    0.84
     matter
    0.82
     conduit
    0.82
    Act Density 0.133%

    No Known Activations