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

    Neuronpedia

    INDEX
    Explanations

    punctuation and significant text markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     most
    -0.41
     MOST
    -0.37
     Wikimedijinoj
    -0.35
    хьтан
    -0.35
    didSet
    -0.33
    最有
    -0.33
    balleur
    -0.33
    beruf
    -0.33
     htmlFor
    -0.32
    Географиясе
    -0.32
    POSITIVE LOGITS
     Meanwhile
    0.82
    Meanwhile
    0.81
     meanwhile
    0.77
    Later
    0.76
     Suddenly
    0.75
    Suddenly
    0.71
     Elsewhere
    0.71
     Later
    0.70
    つづく
    0.69
    ~*~
    0.68
    Act Density 0.358%

    No Known Activations