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

    Neuronpedia

    INDEX
    Explanations

    references to rates and comparisons in contextual discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.06
     Efq
    -0.95
     whoſe
    -0.95
     ſever
    -0.94
     houſe
    -0.92
     Monfieur
    -0.91
    NUMX
    -0.90
     themſelves
    -0.89
     raiſ
    -0.88
     ―――――
    -0.86
    POSITIVE LOGITS
    ,
    0.85
     говоря
    0.55
     main
    0.54
     it
    0.54
    fore
    0.51
     they
    0.51
     she
    0.49
     we
    0.48
     Min
    0.47
    :
    0.45
    Act Density 0.804%

    No Known Activations