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

    Neuronpedia

    INDEX
    Explanations

    quoted strings or dialogue markers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.82
     Majefty
    -1.77
     Efq
    -1.73
     itſelf
    -1.71
     purpoſe
    -1.70
     Jefus
    -1.63
    ſelf
    -1.60
     himſelf
    -1.60
    ſelves
    -1.59
     pleaſure
    -1.59
    POSITIVE LOGITS
      
    0.88
     
    0.87
     “
    0.79
     ‘
    0.79
     '
    0.75
     (
    0.70
    ,
    0.70
     "
    0.69
    :
    0.69
     N
    0.65
    Act Density 0.029%

    No Known Activations