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

    Neuronpedia

    INDEX
    Explanations

    references to encyclopedic or informational content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContextHolder
    -0.17
    engin
    -0.15
    Montserrat
    -0.15
    datap
    -0.14
    rouch
    -0.14
    ÑĦи
    -0.14
    ελ
    -0.13
    iles
    -0.13
    PRS
    -0.13
     mans
    -0.13
    POSITIVE LOGITS
     enc
    0.39
     encyclopedia
    0.37
    Enc
    0.36
     Encyclopedia
    0.36
     Enc
    0.34
    ency
    0.32
    _Enc
    0.30
    lopedia
    0.27
     entry
    0.25
    .Enc
    0.25
    Act Density 0.098%

    No Known Activations