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

    Neuronpedia

    INDEX
    Explanations

    the word "been" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -1.12
     houſe
    -1.08
     Efq
    -1.08
     purpoſe
    -1.00
     scissors
    -0.96
     Houſe
    -0.95
     Viceroy
    -0.94
     becauſe
    -0.92
     myſelf
    -0.92
     esq
    -0.92
    POSITIVE LOGITS
     been
    1.64
     Been
    1.38
    Been
    1.31
    been
    1.15
     BEEN
    1.12
    HasBeen
    0.97
     an
    0.83
     été
    0.80
     a
    0.76
     „
    0.71
    Act Density 0.094%

    No Known Activations