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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events, actions, or descriptions of past events

    oai_token-act-pair · gpt-3.5-turbo

    passive constructions and forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */
    -0.72
    lex
    -0.69
    retty
    -0.67
    Numbers
    -0.67
    TT
    -0.63
    itches
    -0.63
    avier
    -0.63
    oice
    -0.63
    icularly
    -0.60
    @#&
    -0.60
    POSITIVE LOGITS
     plag
    1.24
     supposed
    1.04
     emanating
    0.93
     prevalent
    0.92
     powering
    0.88
     occurring
    0.87
     bothering
    0.86
     endemic
    0.85
     underpin
    0.83
     shaping
    0.83
    Act Density 0.136%

    No Known Activations