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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "pur" and its variations related to purification or purity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eck
    -0.16
    .touches
    -0.15
    acia
    -0.15
    382
    -0.14
    nia
    -0.14
    ë©ĺ
    -0.14
    [sizeof
    -0.14
    μή
    -0.14
    oka
    -0.14
    ei
    -0.14
    POSITIVE LOGITS
    itan
    0.27
    CHASE
    0.25
    veyor
    0.25
    poses
    0.22
    pure
    0.22
    bred
    0.22
    ulent
    0.22
    ging
    0.21
    vey
    0.21
    ported
    0.21
    Act Density 0.006%

    No Known Activations