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

    Neuronpedia

    INDEX
    Explanations

    topics related to various forms of abuse and its impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹Īวมà¸ģ
    -0.16
    ounder
    -0.15
    enal
    -0.15
    OrDefault
    -0.14
    ech
    -0.14
     ãĤ¢ãĤ¤
    -0.14
    gether
    -0.13
    rov
    -0.13
     пом
    -0.13
     nam
    -0.13
    POSITIVE LOGITS
    iveness
    0.18
    uous
    0.15
    erence
    0.15
    383
    0.15
    /man
    0.15
    oldt
    0.14
    æĢ§
    0.14
    åde
    0.14
     manufacture
    0.13
    &A
    0.13
    Act Density 0.060%

    No Known Activations