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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "has" and its variations, emphasizing possession or completion in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Apart
    -0.73
    microsoft
    -0.67
    eem
    -0.64
    ieg
    -0.64
    arity
    -0.64
     branch
    -0.62
     settlement
    -0.60
    abus
    -0.60
     colonial
    -0.59
     blockade
    -0.58
    POSITIVE LOGITS
     been
    1.18
    been
    1.02
     undergone
    0.92
     Been
    0.89
     gotten
    0.88
     risen
    0.87
     gotta
    0.84
     gone
    0.82
     become
    0.81
     plenty
    0.80
    Act Density 0.178%

    No Known Activations