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

    Neuronpedia

    INDEX
    Explanations

    words related to high viewpoints or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "v."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.73
    ãĤ´ãĥ³
    -0.66
     poisoned
    -0.64
     untreated
    -0.62
     Chaser
    -0.60
     poisoning
    -0.60
     Alphabet
    -0.60
    Ô
    -0.59
    Ø©
    -0.58
    éĹĺ
    -0.58
    POSITIVE LOGITS
    arsity
    1.16
    oodoo
    1.14
    ulture
    1.11
    iii
    1.09
    iper
    1.07
    anguard
    1.06
    ibr
    1.05
    alkyrie
    1.02
    ii
    1.00
    iv
    1.00
    Act Density 0.024%

    No Known Activations