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

    Neuronpedia

    INDEX
    Explanations

    references to formal reports and official documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elp
    -0.16
     torch
    -0.15
    inea
    -0.15
    oval
    -0.14
    ër
    -0.14
     Dickinson
    -0.14
    vetica
    -0.13
    ideon
    -0.13
    ags
    -0.13
    gon
    -0.13
    POSITIVE LOGITS
    ázd
    0.15
    Ļ
    0.15
     üzer
    0.14
    ifter
    0.14
    ç»į
    0.14
     Wich
    0.14
    زار
    0.14
    znám
    0.14
    stå
    0.14
    antt
    0.14
    Act Density 0.005%

    No Known Activations