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

    Neuronpedia

    INDEX
    Explanations

    references to evidence or validation of claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Area
    -0.14
    invert
    -0.14
    prene
    -0.14
    ê»ĺ
    -0.14
    quirer
    -0.14
    à¥Ģन
    -0.14
    kir
    -0.14
    odge
    -0.14
    urs
    -0.14
    uteur
    -0.14
    POSITIVE LOGITS
    reading
    0.34
    reader
    0.28
    ed
    0.24
     positive
    0.23
    iness
    0.22
    read
    0.22
    -positive
    0.22
     Positive
    0.20
    ing
    0.20
    READING
    0.20
    Act Density 0.017%

    No Known Activations