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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and punctuation related to dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bragg
    -0.73
     Schot
    -0.72
    straw
    -0.72
     Ballard
    -0.71
    𝐮
    -0.70
    aData
    -0.69
     Schultz
    -0.69
    zelle
    -0.68
    bsd
    -0.68
     Peppermint
    -0.68
    POSITIVE LOGITS
    verwijspagina
    0.90
     iſt
    0.89
    />";
    0.87
     Baf
    0.84
    %"),
    0.83
     moulds
    0.82
    +#+
    0.82
    ſelves
    0.80
     stabilisation
    0.80
     nahilalakip
    0.80
    Act Density 0.263%

    No Known Activations