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

    Neuronpedia

    INDEX
    Explanations

    the word "ke" followed by a number, possibly related to a specific keyword or code pattern in the text

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific prefix or stem in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.69
    ains
    -0.62
    abilities
    -0.61
    oslav
    -0.61
    enegger
    -0.60
    ACY
    -0.59
    ORED
    -0.58
    姫
    -0.58
    ENTS
    -0.57
     Wales
    -0.57
    POSITIVE LOGITS
    pler
    1.17
    ller
    1.16
    jriwal
    1.14
    llers
    1.12
    ez
    1.10
    lling
    1.07
    pee
    1.05
    erk
    1.05
    lp
    1.05
    pper
    1.03
    Act Density 0.025%

    No Known Activations