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

    Neuronpedia

    INDEX
    Explanations

    names of notable individuals and their associated professions or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.16
    lement
    -0.15
    ANDROID
    -0.15
    ismet
    -0.15
    £
    -0.15
    readcr
    -0.14
    eltas
    -0.14
    yntax
    -0.14
     dgv
    -0.14
    .appspot
    -0.14
    POSITIVE LOGITS
     bred
    0.15
    ken
    0.15
     gest
    0.15
     ass
    0.15
     fare
    0.14
     Ross
    0.14
    اÙĩر
    0.14
     Jeh
    0.14
     exits
    0.14
     sec
    0.14
    Act Density 0.013%

    No Known Activations