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

    Neuronpedia

    INDEX
    Explanations

    references to military ranks and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     karak
    -0.16
     پاد
    -0.15
    -ignore
    -0.15
    rani
    -0.15
    irit
    -0.14
    Gratis
    -0.14
    amine
    -0.14
    ildi
    -0.14
    anson
    -0.14
    SizeMode
    -0.13
    POSITIVE LOGITS
     General
    0.28
     Gener
    0.26
     GEN
    0.25
     Gen
    0.25
    General
    0.24
     Joint
    0.23
    eneral
    0.23
    Gener
    0.23
     generals
    0.22
    Gen
    0.21
    Act Density 0.067%

    No Known Activations