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

    Neuronpedia

    INDEX
    Explanations

    themes related to societal expectations and behavioral inconsistencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĿ
    -0.14
    ocal
    -0.14
     pozor
    -0.14
    riv
    -0.14
    werk
    -0.14
    rote
    -0.14
     stron
    -0.13
    Ấ
    -0.13
    rik
    -0.13
    atin
    -0.13
    POSITIVE LOGITS
    _CLI
    0.15
     ìŀIJìĹ°
    0.14
     intermediate
    0.14
    ugar
    0.14
    igest
    0.14
     feather
    0.13
    acre
    0.13
    utter
    0.13
    xon
    0.13
    adiator
    0.13
    Act Density 0.065%

    No Known Activations