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

    Neuronpedia

    INDEX
    Explanations

    the word "con" and its variations, suggesting it tracks contexts of consensus or contention in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.90
    ſelves
    -0.79
    ſelf
    -0.77
     themſelves
    -0.74
     Eſ
    -0.74
     itſelf
    -0.70
     poffible
    -0.69
     leaſt
    -0.66
     pleaſure
    -0.66
    neſs
    -0.64
    POSITIVE LOGITS
     con
    2.87
     com
    0.82
     CON
    0.79
     coi
    0.70
     Con
    0.68
     cons
    0.68
     с
    0.68
     autorytatywna
    0.67
     cun
    0.65
    ----</
    0.64
    Act Density 0.072%

    No Known Activations