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

    Neuronpedia

    INDEX
    Explanations

    key attributes and qualifiers that signal the importance or emphasis of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stav
    -0.16
    ãĤ§
    -0.16
    Advertis
    -0.16
    898
    -0.16
     Ada
    -0.15
    .asp
    -0.15
    .esp
    -0.15
    zac
    -0.14
    eniable
    -0.14
    ulong
    -0.14
    POSITIVE LOGITS
    ekte
    0.18
     Credit
    0.16
    YT
    0.15
    ndon
    0.15
     credit
    0.14
     typ
    0.14
    onu
    0.14
    typ
    0.14
    igne
    0.14
     La
    0.14
    Act Density 0.001%

    No Known Activations