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

    Neuronpedia

    INDEX
    Explanations

    the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.00
     ſever
    -0.99
     ſtate
    -0.99
     myſelf
    -0.98
     Chriftian
    -0.97
     raiſ
    -0.96
     pleaſure
    -0.93
     houſe
    -0.91
     ſeveral
    -0.91
     themſelves
    -0.90
    POSITIVE LOGITS
     is
    1.93
     was
    1.42
     are
    1.38
     not
    1.31
     Is
    1.19
     also
    1.18
     be
    1.16
     being
    1.14
     has
    1.09
     IS
    1.09
    Act Density 0.921%

    No Known Activations