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

    Neuronpedia

    INDEX
    Explanations

    references to euphemisms or indirect language around difficult topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oneofs
    -0.99
     <<<<<<<<<<<<<<
    -0.74
    出版年
    -0.67
    gifs
    -0.66
    mphs
    -0.66
     Blazers
    -0.65
    belts
    -0.65
     intptr
    -0.64
    UMNS
    -0.64
    adaptiveStyles
    -0.63
    POSITIVE LOGITS
     âmes
    0.84
     délais
    0.80
     dieux
    0.79
     prochaines
    0.77
     genoux
    0.71
     vœux
    0.70
     oreilles
    0.69
     blessés
    0.69
     écrits
    0.67
     nuages
    0.67
    Act Density 0.687%

    No Known Activations