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

    Neuronpedia

    INDEX
    Explanations

    references to reflection on past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obus
    -0.19
     Bridge
    -0.15
    oku
    -0.15
    enties
    -0.15
    yll
    -0.15
    hap
    -0.14
    ourage
    -0.14
     dö
    -0.14
     brid
    -0.14
    Bridge
    -0.14
    POSITIVE LOGITS
    IPH
    0.15
    ister
    0.15
    èī
    0.15
    ith
    0.14
    htable
    0.14
    бина
    0.14
    ISTER
    0.14
    elp
    0.14
    ÑĸÑĶ
    0.14
    wards
    0.13
    Act Density 0.018%

    No Known Activations