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

    Neuronpedia

    INDEX
    Explanations

    information related to user agreements and consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reperto
    -0.77
     troop
    -0.69
     barracks
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
     carbs
    -0.68
    oldown
    -0.67
     dens
    -0.64
    adish
    -0.64
     grains
    -0.64
     rust
    -0.63
    POSITIVE LOGITS
     hereby
    1.05
     Sponsor
    1.04
     indemn
    0.96
     Agreement
    0.91
     trademarks
    0.90
     disclaim
    0.90
     goodwill
    0.87
     Participant
    0.86
     Warranty
    0.85
     Regist
    0.85
    Act Density 0.115%

    No Known Activations