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

    Neuronpedia

    INDEX
    Explanations

    patterns and formats related to structured data or software versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onis
    -0.15
    éĥİ
    -0.15
    UNUSED
    -0.15
    uja
    -0.15
    ξη
    -0.15
    oose
    -0.14
    nze
    -0.14
    ifo
    -0.14
    ivate
    -0.14
    YLE
    -0.14
    POSITIVE LOGITS
    arpa
    0.15
    jadi
    0.15
    arb
    0.15
    deb
    0.14
     hygiene
    0.14
    못
    0.13
    bate
    0.13
     Dil
    0.13
     示
    0.13
    babel
    0.13
    Act Density 0.104%

    No Known Activations