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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.73
     Walkover
    -0.65
    recated
    -0.64
     OFDb
    -0.61
     myſelf
    -0.59
     Normdatei
    -0.56
    Viitteet
    -0.56
     transfieras
    -0.56
     queſta
    -0.55
     arşivlendi
    -0.54
    POSITIVE LOGITS
     twofold
    0.49
    在于
    0.35
     threefold
    0.35
     Unternehmens
    0.33
    scaled
    0.33
    BRD
    0.32
     уди
    0.31
     yks
    0.31
    ่า
    0.31
    Scaled
    0.31
    Act Density 0.207%

    No Known Activations