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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or well-wishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.58
    thâu
    -0.56
    UnknownFieldSet
    -0.56
     WebDriverWait
    -0.53
    ﷺ
    -0.52
    XmlAccessorType
    -0.51
     незавершена
    -0.51
    Wird
    -0.50
     modelAndView
    -0.49
     lisesi
    -0.48
    POSITIVE LOGITS
     reiterate
    0.87
     remind
    0.84
     clarify
    0.77
     mention
    0.76
     briefly
    0.69
     emphasize
    0.66
     emphasise
    0.66
     reminding
    0.66
     warn
    0.65
    remind
    0.65
    Act Density 0.167%

    No Known Activations