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

    Neuronpedia

    INDEX
    Explanations

    parenthetical expressions and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raiſ
    -0.66
     ſever
    -0.63
     myſelf
    -0.63
     deſt
    -0.61
     ſhe
    -0.56
     juſ
    -0.55
     faſt
    -0.54
     ſtand
    -0.54
     anſ
    -0.54
     ſee
    -0.54
    POSITIVE LOGITS
     theirs
    0.48
     hers
    0.45
     ours
    0.39
    Yours
    0.38
     yours
    0.37
    affaire
    0.36
     évidence
    0.36
    yours
    0.35
     nôtre
    0.34
    zī
    0.33
    Act Density 0.278%

    No Known Activations