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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.20
     Jefus
    -1.05
     pleaſure
    -0.97
     myſelf
    -0.94
     themſelves
    -0.93
     purpoſe
    -0.91
     houſe
    -0.91
     Efq
    -0.90
     whoſe
    -0.90
     fufficient
    -0.90
    POSITIVE LOGITS
     be
    1.26
     able
    1.04
     бъдат
    0.78
     Be
    0.78
     être
    0.77
     BE
    0.77
    Be
    0.76
    ToBe
    0.76
    be
    0.74
     бъде
    0.73
    Act Density 0.154%

    No Known Activations