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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-presentation and validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illet
    -0.17
    sembles
    -0.16
    illos
    -0.16
    ohana
    -0.15
    neath
    -0.15
    eman
    -0.15
    ugu
    -0.14
     Dough
    -0.14
     Dock
    -0.14
     CRC
    -0.14
    POSITIVE LOGITS
    uet
    0.15
    ÑĥлÑĮ
    0.15
    767
    0.15
    yal
    0.15
    PointerException
    0.14
    quip
    0.14
    èħ¦
    0.14
    à¤ľà¤°
    0.14
    964
    0.14
     ê·¸ëŁ°
    0.14
    Act Density 0.339%

    No Known Activations