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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or humor in casual conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referenties
    -0.77
     فريبيس
    -0.77
     BoxDecoration
    -0.72
     BrowserModule
    -0.72
    RenderAtEndOf
    -0.71
     怎样
    -0.70
     themſelves
    -0.66
     ComVisible
    -0.66
     |]
    -0.66
     ➢
    -0.65
    POSITIVE LOGITS
     fuckin
    0.62
     fucking
    0.61
     freakin
    0.59
     G
    0.58
     FUCKING
    0.57
    g
    0.56
     Mar
    0.56
     forgive
    0.55
    modium
    0.55
     BRO
    0.54
    Act Density 0.170%

    No Known Activations