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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration and compliments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    łbym
    -1.02
    僕も
    -0.85
    ครับ
    -0.80
    俺は
    -0.80
    ผม
    -0.79
    łem
    -0.78
     ผม
    -0.77
    MfG
    -0.77
    僕の
    -0.75
    こいつ
    -0.73
    POSITIVE LOGITS
     désol
    0.79
    łam
    0.74
     gorgeous
    0.73
    Obrigada
    0.73
     hubby
    0.69
     marito
    0.68
     marido
    0.66
     xoxo
    0.66
     sparkly
    0.65
     lovely
    0.65
    Act Density 1.893%

    No Known Activations