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

    Neuronpedia

    INDEX
    Explanations

    pronouns related to people and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.89
     in
    -0.72
     of
    -0.70
     the
    -0.67
     a
    -0.67
     is
    -0.65
     at
    -0.64
     then
    -0.63
     not
    -0.60
     are
    -0.60
    POSITIVE LOGITS
     Paglinawan
    1.06
    Autoritní
    0.93
    aarrggbb
    0.86
    riwal
    0.85
    tvguidetime
    0.79
     ligiloj
    0.76
     vectra
    0.74
    +#+#
    0.74
     meriva
    0.72
     kaarangay
    0.71
    Act Density 0.419%

    No Known Activations