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

    Neuronpedia

    INDEX
    Explanations

    prefixes and suffixes related to programming or scripting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YPRE
    -0.18
    éric
    -0.16
    taÅŁ
    -0.15
    isman
    -0.14
    roje
    -0.14
     Crown
    -0.14
    itarian
    -0.14
    iners
    -0.14
    eniz
    -0.13
    hower
    -0.13
    POSITIVE LOGITS
    aching
    0.36
    ached
    0.36
    aches
    0.33
    ache
    0.33
    achable
    0.32
    fg
    0.31
    allback
    0.28
    leanup
    0.26
    pu
    0.26
    redentials
    0.26
    Act Density 0.057%

    No Known Activations