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

    Neuronpedia

    INDEX
    Explanations

    references to testing and injection in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isson
    -0.15
    cast
    -0.15
    ake
    -0.15
    caster
    -0.14
    alled
    -0.14
    mage
    -0.14
    elon
    -0.14
    ison
    -0.14
    .getObject
    -0.13
     Creatures
    -0.13
    POSITIVE LOGITS
    ;↵↵
    0.20
    .decor
    0.17
    ango
    0.16
    .sd
    0.15
    ¤¤
    0.14
    ;↵
    0.14
    teÅŁ
    0.14
    wal
    0.14
    ANS
    0.14
     دÙĨ
    0.14
    Act Density 0.009%

    No Known Activations