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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs and forms of "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    A
    -0.46
    abstractmethod
    -0.43
     ministres
    -0.42
    torem
    -0.42
    一会
    -0.42
    All
    -0.42
     offending
    -0.42
     superiori
    -0.42
    The
    -0.42
    “
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.83
    =$?
    0.77
     Infórmanos
    0.76
    UserScript
    0.75
    matchCondition
    0.74
     مرئيه
    0.70
     дописавши
    0.69
    +#+#
    0.68
     saites
    0.68
     '\\;'
    0.68
    Act Density 0.462%

    No Known Activations