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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating personal perspective and involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '},
    -0.86
    "){
    -0.81
    =")
    -0.81
    SequentialGroup
    -0.79
    ]<<
    -0.79
    '){
    -0.76
    %")
    -0.75
    */;
    -0.75
    AddTagHelper
    -0.75
    blest
    -0.75
    POSITIVE LOGITS
    ,
    0.70
     us
    0.66
    .
    0.66
     moi
    0.63
     sendiri
    0.62
     him
    0.61
     me
    0.61
     nobis
    0.58
    us
    0.56
     myself
    0.55
    Act Density 0.118%

    No Known Activations