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

    Neuronpedia

    INDEX
    Explanations

    terms related to social constructs and cultural critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acet
    -0.15
    »¿
    -0.15
    irt
    -0.15
     itemprop
    -0.14
     reversible
    -0.14
     mã
    -0.14
     (++
    -0.14
    fore
    -0.13
    ilon
    -0.13
    eten
    -0.13
    POSITIVE LOGITS
     ar
    0.17
     Agency
    0.15
    éĥ¡
    0.15
    velt
    0.14
    itat
    0.14
    nesday
    0.14
     ÏĦÏĮ
    0.14
     Organisation
    0.14
     dw
    0.13
     POSSIBILITY
    0.13
    Act Density 0.667%

    No Known Activations