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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate positive attributes and qualities in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     насељу
    -0.39
     ligiloj
    -0.36
    كويكب
    -0.35
    干
    -0.34
    Handlung
    -0.34
    mania
    -0.33
    お
    -0.32
    isContained
    -0.32
    といい
    -0.31
     communiquez
    -0.31
    POSITIVE LOGITS
     bouts
    0.80
     bursts
    0.63
     bout
    0.63
    bouts
    0.63
    webElementXpaths
    0.63
    RectangleBorder
    0.61
     ſind
    0.59
    yntaxException
    0.57
     myſelf
    0.57
     ***!
    0.56
    Act Density 0.921%

    No Known Activations