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

    Neuronpedia

    INDEX
    Explanations

    expressions that emphasize the significance or importance of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uffers
    -0.19
    stav
    -0.16
    ivery
    -0.15
    rav
    -0.15
    ppard
    -0.15
    Deserializer
    -0.15
    enberg
    -0.15
    positor
    -0.15
    ElementException
    -0.14
    ils
    -0.14
    POSITIVE LOGITS
    ikt
    0.16
    okus
    0.15
    ingly
    0.15
    fully
    0.15
    ìĦŃ
    0.14
     me
    0.14
    ensi
    0.14
    eer
    0.14
    ìŀĶ
    0.14
     greatly
    0.13
    Act Density 0.031%

    No Known Activations