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

    Neuronpedia

    INDEX
    Explanations

    references to actions or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijken
    -0.15
    itters
    -0.15
    ropping
    -0.14
     Xm
    -0.14
    VERY
    -0.14
    583
    -0.14
    меÑĤÑĮ
    -0.14
     Clarkson
    -0.14
    .await
    -0.14
     Frid
    -0.13
    POSITIVE LOGITS
    eh
    0.18
    rama
    0.17
     otherwise
    0.16
    ModelAttribute
    0.16
    agram
    0.16
    anton
    0.15
    ules
    0.14
    feld
    0.14
    Äįet
    0.14
    aison
    0.14
    Act Density 0.019%

    No Known Activations