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

    Neuronpedia

    INDEX
    Explanations

    V-shaped objects or concepts

    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
    -0.62
     shortened
    -0.59
     poisoning
    -0.58
    Ø©
    -0.58
     evenings
    -0.58
    nels
    -0.58
     apprehension
    -0.58
    éĹĺ
    -0.57
    Favorite
    -0.57
    etheless
    -0.57
    POSITIVE LOGITS
    arsity
    1.22
    ulture
    1.16
    oodoo
    1.16
    iii
    1.12
    anguard
    1.11
    iper
    1.04
    ibr
    1.03
    ii
    1.01
    apers
    1.01
    aunted
    1.00
    Act Density 0.018%

    No Known Activations