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

    Neuronpedia

    INDEX
    Explanations

    phrases that center around the verb "be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     being
    -0.55
     sendo
    -0.53
    AnchorStyles
    -0.52
    being
    -0.51
     siendo
    -0.50
     "..\..\..\
    -0.47
    necessary
    -0.46
     być
    -0.46
     "..\..\
    -0.45
     enough
    -0.45
    POSITIVE LOGITS
     contd
    0.76
     otomatig
    0.76
     reckoned
    0.75
     للمعارف
    0.74
    Билгалдахарш
    0.71
     HasFactory
    0.69
     exact
    0.66
     honest
    0.65
    :✨
    0.65
     uſed
    0.64
    Act Density 0.142%

    No Known Activations