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
     itſelf
    -1.04
     Majefty
    -0.91
     themſelves
    -0.87
     raiſ
    -0.86
     fubject
    -0.85
     alſo
    -0.84
     myſelf
    -0.84
     uſed
    -0.84
     Reſ
    -0.84
     houſe
    -0.84
    POSITIVE LOGITS
     the
    0.91
     a
    0.79
     “
    0.75
     ‘
    0.63
    └──
    0.61
     "
    0.60
     an
    0.60
     different
    0.59
    的是
    0.57
     j
    0.55
    Act Density 0.052%

    No Known Activations