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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that signify significant entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irez
    -0.17
    hack
    -0.15
    idel
    -0.15
    noc
    -0.14
     OVERRIDE
    -0.14
    157
    -0.14
    æķĻ
    -0.14
    çĭĤ
    -0.14
    inee
    -0.13
     Emanuel
    -0.13
    POSITIVE LOGITS
    logan
    0.17
    agner
    0.16
    embedded
    0.15
    iola
    0.15
    ardin
    0.15
     pic
    0.15
     Embedded
    0.15
    ÏĢλα
    0.14
    éĽĦ
    0.14
     embedded
    0.14
    Act Density 0.001%

    No Known Activations