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

    Neuronpedia

    INDEX
    Explanations

    specific details related to legal cases and personal information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.73
    mbuds
    -0.73
    :#
    -0.66
    ģ«
    -0.64
    ======
    -0.63
    stuff
    -0.62
    ł
    -0.62
    ESE
    -0.61
    urgy
    -0.61
    icter
    -0.60
    POSITIVE LOGITS
     who
    0.92
     pleaded
    0.89
     died
    0.85
     whose
    0.83
     of
    0.79
     whom
    0.77
     suffers
    0.76
     grandson
    0.74
     remembers
    0.74
     aka
    0.73
    Act Density 0.078%

    No Known Activations