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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to programming and technical explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.64
     Theſe
    -1.64
     Efq
    -1.61
     Cæsar
    -1.60
     Anſ
    -1.57
     ―――――
    -1.56
     CHAPITRE
    -1.54
     Houſe
    -1.49
     Diſ
    -1.47
     Reſ
    -1.45
    POSITIVE LOGITS
     de
    0.91
     en
    0.79
     est
    0.77
     la
    0.71
     con
    0.71
     que
    0.70
     ya
    0.69
     es
    0.68
     entre
    0.66
     una
    0.65
    Act Density 0.169%

    No Known Activations