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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roperties
    -0.16
    ikan
    -0.16
    /***/
    -0.15
    ologna
    -0.14
    awah
    -0.14
    .documentation
    -0.14
     bankrupt
    -0.14
    alama
    -0.14
    à¹ģà¸ŀ
    -0.14
    ÑĢÑĸз
    -0.13
    POSITIVE LOGITS
    elden
    0.19
    oky
    0.17
     necessarily
    0.15
    okies
    0.15
     anymore
    0.14
    ught
    0.14
    ington
    0.14
    lder
    0.14
    ãĥ³ãĥĪ
    0.14
    chie
    0.14
    Act Density 0.040%

    No Known Activations