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

    Neuronpedia

    INDEX
    Explanations

    terms related to irreversibility and significant, often permanent changes or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kla
    -0.18
    ETCH
    -0.17
    jin
    -0.15
    رÙĬ
    -0.15
    reau
    -0.15
    etch
    -0.15
    ẻ
    -0.15
    ÑĥÑĢа
    -0.15
    .Priority
    -0.15
    bine
    -0.15
    POSITIVE LOGITS
    press
    0.25
    trie
    0.25
    parable
    0.24
    conc
    0.22
     irre
    0.20
    vers
    0.20
    duc
    0.19
    ver
    0.18
    lev
    0.18
    ducible
    0.18
    Act Density 0.004%

    No Known Activations