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

    Neuronpedia

    INDEX
    Explanations

    the word "anks" at the end of words

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific term or concept related to "banks."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifetime
    -0.70
     vide
    -0.64
     witness
    -0.64
     Nova
    -0.62
     strictly
    -0.62
     reprodu
    -0.61
     keynote
    -0.61
     address
    -0.61
     omn
    -0.60
    CONT
    -0.60
    POSITIVE LOGITS
    anks
    4.56
    anking
    2.54
    ANK
    2.34
    anked
    2.32
    ank
    2.21
    inks
    1.23
    anges
    1.20
    banks
    1.17
    ushes
    1.14
    anka
    1.09
    Act Density 0.010%

    No Known Activations