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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     @}
    -0.65
     Els
    -0.63
    batore
    -0.56
    SOUNDBITE
    -0.55
     numerus
    -0.54
    ffron
    -0.54
     CURIAM
    -0.54
     zwar
    -0.53
    Els
    -0.53
    __((
    -0.52
    POSITIVE LOGITS
     Просто
    0.78
     Simplemente
    0.76
     semplici
    0.74
     basta
    0.67
    单纯
    0.65
     незавершена
    0.63
    Simply
    0.63
     lamang
    0.63
     simplesmente
    0.62
     egyszerű
    0.61
    Act Density 0.208%

    No Known Activations