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

    Neuronpedia

    INDEX
    Explanations

    references to regulations and governance structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ji
    -0.14
    esh
    -0.13
    mens
    -0.13
    Ì
    -0.13
    nes
    -0.13
    ty
    -0.13
    oy
    -0.13
    vern
    -0.13
    mn
    -0.13
    ABC
    -0.12
    POSITIVE LOGITS
     programme
    0.19
     project
    0.17
     program
    0.17
    ácil
    0.16
    uddle
    0.16
     committee
    0.16
    plode
    0.15
    andler
    0.15
    plugin
    0.15
    ĥĿ
    0.15
    Act Density 2.026%

    No Known Activations