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

    Neuronpedia

    INDEX
    Explanations

    references to a specific testing or programming framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.77
     виправивши
    -0.70
     المعيارى
    -0.70
     himo
    -0.64
     übersch
    -0.59
     NTIS
    -0.58
     Sitting
    -0.57
     незавершена
    -0.57
     Tame
    -0.57
    stateProvider
    -0.56
    POSITIVE LOGITS
    MU
    0.80
     MU
    0.72
    café
    0.69
    cafe
    0.67
     mu
    0.67
     MT
    0.66
     cafe
    0.66
     café
    0.63
    Cafe
    0.62
    Mu
    0.61
    Act Density 0.144%

    No Known Activations