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

    Neuronpedia

    INDEX
    Explanations

    references to long-term considerations or strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.93
     Roskov
    -0.72
    Hentet
    -0.69
    ГЛА
    -0.67
    RTLR
    -0.67
     Walkover
    -0.66
     bezeichneter
    -0.61
     compét
    -0.61
     mourut
    -0.61
     surla
    -0.60
    POSITIVE LOGITS
     longterm
    1.17
    fristi
    0.93
    長期
    0.86
    fristig
    0.84
    term
    0.77
    长期
    0.75
     permanent
    0.69
     jangka
    0.67
    xaml
    0.66
     long
    0.61
    Act Density 0.229%

    No Known Activations