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

    Neuronpedia

    INDEX
    Explanations

    references to reminders or significant lessons learned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.08
    7:0.07
    8:0.07
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
    undown
    -1.79
    amping
    -1.77
    Problem
    -1.72
    arters
    -1.69
    Discuss
    -1.66
     Ack
    -1.65
    anguage
    -1.61
    エル
    -1.60
    iven
    -1.60
    Translation
    -1.59
    POSITIVE LOGITS
     FD
    1.77
     Sloan
    1.75
     Milton
    1.64
     Pilgrim
    1.64
     Mellon
    1.60
     Mechdragon
    1.58
     Mons
    1.55
     congrat
    1.54
     depos
    1.50
     Martha
    1.48
    Act Density 0.000%

    No Known Activations