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

    Neuronpedia

    INDEX
    Explanations

    important events or changes

    oai_token-act-pair · gpt-3.5-turbo

    the word "has" in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interested
    -0.66
    eem
    -0.61
    atically
    -0.60
     Apart
    -0.54
     observing
    -0.54
     nu
    -0.53
     Pair
    -0.53
    ances
    -0.52
     behold
    -0.52
     poking
    -0.51
    POSITIVE LOGITS
     been
    1.39
    been
    1.22
     undergone
    1.19
    kell
    1.08
     risen
    1.05
     Been
    1.05
     become
    1.03
    bara
    1.03
     arisen
    1.02
     emerged
    0.98
    Act Density 0.316%

    No Known Activations