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

    Neuronpedia

    INDEX
    Explanations

    phrases related to new or incoming events or people

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to incoming and outgoing elements, especially in the context of administrations and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifications
    -0.70
    arily
    -0.69
    illance
    -0.68
    ching
    -0.67
    arist
    -0.67
    ghazi
    -0.67
    ovember
    -0.66
    rolling
    -0.66
    nington
    -0.66
    udder
    -0.65
    POSITIVE LOGITS
     freshmen
    0.97
     freshman
    0.86
     president
    0.79
     administrations
    0.79
     Presidents
    0.77
     arrivals
    0.77
     occupant
    0.72
     presidents
    0.71
     entrants
    0.70
    lus
    0.69
    Act Density 0.045%

    No Known Activations