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

    Neuronpedia

    INDEX
    Explanations

    references to societal structures and their impact on individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etus
    -0.22
    ena
    -0.17
    enus
    -0.14
    úc
    -0.14
    stddef
    -0.14
    pta
    -0.14
    olk
    -0.14
    endi
    -0.13
    memberOf
    -0.13
    vault
    -0.13
    POSITIVE LOGITS
    phin
    0.17
    ινÏĮ
    0.16
    coop
    0.16
    ataire
    0.15
    uada
    0.14
    OBJ
    0.14
    оÑĢÑıд
    0.14
    ertas
    0.14
    opsis
    0.14
    itize
    0.14
    Act Density 0.440%

    No Known Activations