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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and phrases related to authority and agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .nano
    -0.18
    idge
    -0.16
    ucc
    -0.15
    inas
    -0.15
    ksen
    -0.14
     proceeds
    -0.14
    AMI
    -0.14
     ún
    -0.13
     Sweat
    -0.13
    thon
    -0.13
    POSITIVE LOGITS
    å¡Ķ
    0.18
    LAR
    0.17
    atcher
    0.16
    buah
    0.15
    sen
    0.15
    odel
    0.15
    Slides
    0.14
    Rotor
    0.14
    lar
    0.14
    uf
    0.14
    Act Density 0.006%

    No Known Activations