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

    Neuronpedia

    INDEX
    Explanations

    statements contrasting different perspectives or qualities

    oai_token-act-pair · gpt-3.5-turbo

    assertions or statements about reality and conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.68
    ãĥĺ
    -0.63
     favourites
    -0.61
     Uniform
    -0.58
     Eps
    -0.58
     Mile
    -0.57
     unsolved
    -0.57
     unused
    -0.57
     Vand
    -0.57
     favorites
    -0.56
    POSITIVE LOGITS
    Rather
    0.96
    isite
    0.87
    gemony
    0.85
     Rather
    0.81
    actually
    0.79
    rather
    0.78
    're
    0.78
    ÃŃs
    0.77
    inis
    0.72
     actually
    0.72
    Act Density 0.149%

    No Known Activations