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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms that describe accuracy, efficiency, and timeliness in processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herits
    -0.16
    atch
    -0.15
    گاÙĨ
    -0.14
    UTILITY
    -0.14
    ëĿ
    -0.13
    ãĥĶãĥ¼
    -0.13
    ìĥģìľĦ
    -0.13
    ëĨ
    -0.13
    ÑĢазÑĥ
    -0.13
    CEPTION
    -0.12
    POSITIVE LOGITS
     fashion
    0.73
     manner
    0.71
     way
    0.58
     Fashion
    0.51
    -fashion
    0.48
    Fashion
    0.44
     manners
    0.42
     mann
    0.41
    ashion
    0.40
     matter
    0.39
    Act Density 0.078%

    No Known Activations