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

    Neuronpedia

    INDEX
    Explanations

    phrases related to implicit meanings and suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iales
    -0.17
    管
    -0.15
    rum
    -0.15
    æĿ
    -0.15
    ãĤ¤ãĥī
    -0.15
    祥
    -0.15
    VERR
    -0.14
    erras
    -0.14
    Prince
    -0.14
    мена
    -0.14
    POSITIVE LOGITS
    _Ptr
    0.14
     dri
    0.14
     indirectly
    0.13
    578
    0.13
     dust
    0.13
     packed
    0.13
    829
    0.13
    ql
    0.13
    705
    0.13
     wards
    0.13
    Act Density 0.171%

    No Known Activations