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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Posted" indicating articles or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pe
    -0.19
     e
    -0.15
     unw
    -0.15
     Pe
    -0.15
    dorf
    -0.14
    ãĥ¼ãĤ¯
    -0.14
     r
    -0.14
     gut
    -0.14
    toa
    -0.14
    owitz
    -0.14
    POSITIVE LOGITS
    ÑĪÑĤов
    0.15
    mars
    0.15
    FormsModule
    0.15
     αÏģ
    0.14
    ombok
    0.14
    URN
    0.14
    ìĺĪ
    0.14
    ENCED
    0.14
    /tiny
    0.14
    eddar
    0.14
    Act Density 0.001%

    No Known Activations