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

    Neuronpedia

    INDEX
    Explanations

    references to uprisings and rebellions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifact
    -0.15
    ãĥ§
    -0.15
    ysz
    -0.15
    aign
    -0.15
    mium
    -0.14
    setLabel
    -0.14
    factor
    -0.14
    EMPLARY
    -0.14
    ulg
    -0.14
    headline
    -0.14
    POSITIVE LOGITS
    aller
    0.18
    Opcode
    0.15
    Occurrences
    0.15
    je
    0.15
    jen
    0.14
     Parenthood
    0.14
    unan
    0.14
    QUIRE
    0.14
    .try
    0.13
    ana
    0.13
    Act Density 0.037%

    No Known Activations