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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __((
    -0.67
     certainly
    -0.62
    caux
    -0.62
     @}
    -0.61
    Autoritní
    -0.61
    ocarditis
    -0.61
    enchymal
    -0.59
    aarrggbb
    -0.58
    httphttps
    -0.58
     numerus
    -0.57
    POSITIVE LOGITS
     basta
    0.59
     Просто
    0.56
     plain
    0.55
    单纯
    0.54
    ManagedBean
    0.53
    ợi
    0.53
    THISDAY
    0.52
     semplici
    0.52
     Just
    0.51
    Just
    0.51
    Act Density 0.161%

    No Known Activations