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

    Neuronpedia

    INDEX
    Explanations

    references to methods in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rt
    -0.15
    iff
    -0.15
    ilis
    -0.14
    lod
    -0.14
    cone
    -0.14
    werk
    -0.14
    λÏħ
    -0.14
     nett
    -0.14
    -0.14
    EA
    -0.14
    POSITIVE LOGITS
    olle
    0.18
    implify
    0.16
    /Foundation
    0.15
     Primitive
    0.15
    ãĤ¹ãĤ¯
    0.15
    ãĥ¡ãĥ©
    0.15
    ugi
    0.15
    obe
    0.14
    вен
    0.14
    عر
    0.14
    Act Density 0.029%

    No Known Activations