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

    Neuronpedia

    INDEX
    Explanations

    instances of embarrassment or socially awkward situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.62
     насељу
    -0.55
     שוליים
    -0.51
    enumii
    -0.48
     avid
    -0.47
    regado
    -0.47
     PyLong
    -0.47
     pouss
    -0.47
     Benedikt
    -0.47
     fapt
    -0.46
    POSITIVE LOGITS
     embarrassment
    0.90
     embarrassed
    0.83
    Embar
    0.80
     Embar
    0.79
     appearance
    0.79
    المناصب
    0.77
     embarrassing
    0.74
     Etiquette
    0.74
     Appearance
    0.73
     etiquette
    0.73
    Act Density 0.343%

    No Known Activations