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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èm
    -0.18
    竹
    -0.18
    ANJI
    -0.16
    indent
    -0.14
    hl
    -0.14
    reau
    -0.14
    ers
    -0.14
    erry
    -0.13
    емон
    -0.13
    éĽħ
    -0.13
    POSITIVE LOGITS
    /disable
    0.17
    -plugins
    0.16
    ehir
    0.16
    -bodied
    0.15
    iasm
    0.15
    rosse
    0.15
    ouce
    0.14
    inus
    0.14
    تÙĦ
    0.14
    .cloudflare
    0.14
    Act Density 0.061%

    No Known Activations