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

    Neuronpedia

    INDEX
    Explanations

    elements related to safety procedures and demonstrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oller
    -0.15
    iaux
    -0.15
     margin
    -0.15
    åĴ²
    -0.14
    reso
    -0.14
     sem
    -0.14
    atsu
    -0.14
     stup
    -0.14
    fluid
    -0.14
    orex
    -0.14
    POSITIVE LOGITS
     Toast
    0.15
    ê¶Į
    0.15
     podium
    0.15
    uten
    0.14
    мин
    0.14
     intro
    0.14
     introduction
    0.14
     ga
    0.14
     intros
    0.14
    ige
    0.13
    Act Density 0.312%

    No Known Activations