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

    Neuronpedia

    INDEX
    Explanations

    links or references to related topics within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to additional information or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.82
     enthusi
    -0.79
    oppers
    -0.76
    Redd
    -0.71
    jl
    -0.69
    iannopoulos
    -0.69
    ecd
    -0.66
    anova
    -0.66
    ilst
    -0.64
    Shares
    -0.64
    POSITIVE LOGITS
     Grave
    0.94
     Martial
    0.86
     Unc
    0.82
     Defeat
    0.77
     Edit
    0.74
     Nig
    0.73
     Gloss
    0.73
     References
    0.71
     Appendix
    0.71
     supra
    0.70
    Act Density 0.038%

    No Known Activations