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

    Neuronpedia

    INDEX
    Explanations

    sentence-ending punctuation, indicating conclusions or significant statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unden
    -0.83
     veter
    -0.82
     ancest
    -0.76
     skelet
    -0.76
     glim
    -0.74
     predec
    -0.73
     tremend
    -0.71
     psychiat
    -0.71
     unemploy
    -0.70
     perspect
    -0.69
    POSITIVE LOGITS
     Heck
    0.78
     Granted
    0.70
     Appropri
    0.70
     Opp
    0.69
     Occasionally
    0.69
     Removal
    0.68
     Ultimately
    0.66
     Amen
    0.65
     However
    0.65
     RELEASE
    0.65
    Act Density 0.226%

    No Known Activations