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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with the phrase "In short" and contain a succinct statement

    oai_token-act-pair · gpt-3.5-turbo

    introductory phrases signaling a summary or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.90
    Pg
    -0.76
    Already
    -0.65
    )</
    -0.64
    rals
    -0.64
    Äĩ
    -0.61
     Archdemon
    -0.61
    Ãį
    -0.61
    Rated
    -0.61
    oubted
    -0.60
    POSITIVE LOGITS
     SPACE
    0.78
     nutshell
    0.74
     ACTIONS
    0.73
     LET
    0.71
     Solitaire
    0.71
     Whoever
    0.70
     Restore
    0.69
    ymm
    0.68
     STOP
    0.67
     Spaces
    0.66
    Act Density 0.139%

    No Known Activations