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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters or official statements

    oai_token-act-pair · gpt-3.5-turbo

    the repeated usage of the phrase "has" indicating ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eem
    -0.69
    atically
    -0.66
     Apart
    -0.66
    —-
    -0.62
    icking
    -0.60
    catentry
    -0.59
    etting
    -0.59
    ove
    -0.57
    ancing
    -0.55
    Subject
    -0.54
    POSITIVE LOGITS
     been
    1.49
    been
    1.19
     undergone
    1.16
     become
    1.07
     begun
    1.05
     gotten
    1.02
     gone
    0.98
     emerged
    0.97
     Been
    0.95
    kell
    0.94
    Act Density 0.389%

    No Known Activations