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

    Neuronpedia

    INDEX
    Explanations

    words related to describing actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is" or variations of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Highlights
    -0.69
    pedia
    -0.69
     Raise
    -0.66
    sonian
    -0.65
     Hitch
    -0.65
    inav
    -0.64
     Letters
    -0.64
    âĢİ
    -0.63
    ths
    -0.62
     Reports
    -0.62
    POSITIVE LOGITS
    nt
    1.20
     deemed
    0.92
     supposed
    0.88
     already
    0.85
     treated
    0.85
     able
    0.85
     undet
    0.84
     unable
    0.84
     taken
    0.83
     indistinguishable
    0.81
    Act Density 0.387%

    No Known Activations