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

    Neuronpedia

    INDEX
    Explanations

    information related to people's current or upcoming activities, such as being on tour, entering a new season, making a film, or preparing for a fight

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events or actions occurring in the present

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    they
    -0.76
    them
    -0.72
    each
    -0.67
     selves
    -0.65
    together
    -0.63
    selves
    -0.61
    everyone
    -0.60
    these
    -0.59
    They
    -0.59
     alike
    -0.57
    POSITIVE LOGITS
     his
    1.24
     himself
    1.11
     retirement
    0.99
    his
    0.92
     HIS
    0.91
     extradition
    0.84
     her
    0.84
     reelection
    0.82
    His
    0.81
     autobiography
    0.81
    Act Density 0.377%

    No Known Activations