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

    Neuronpedia

    INDEX
    Explanations

    references to various aspects of culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ity
    -0.22
    ities
    -0.18
    ../../../
    -0.18
    idade
    -0.17
    rega
    -0.16
    rone
    -0.16
    itis
    -0.16
    ida
    -0.15
    nie
    -0.15
    ifier
    -0.15
    POSITIVE LOGITS
    urum
    0.21
     shock
    0.20
    lle
    0.20
    urally
    0.19
    .scalablytyped
    0.18
    anzi
    0.17
    urre
    0.17
    /history
    0.17
    ured
    0.16
     Shock
    0.16
    Act Density 0.024%

    No Known Activations