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

    Neuronpedia

    INDEX
    Explanations

    references to political party affiliations and legislative roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ic
    -0.20
    e
    -0.18
    y
    -0.18
    i
    -0.16
    uelle
    -0.15
    iÄĩ
    -0.15
    er
    -0.15
    itten
    -0.15
    charted
    -0.15
    elin
    -0.14
    POSITIVE LOGITS
    ifornia
    0.28
    iforn
    0.26
    adays
    0.18
    ifi
    0.16
    culator
    0.16
    IF
    0.16
    iform
    0.16
    ahoma
    0.16
    inia
    0.15
    ãĤ´ãĥª
    0.15
    Act Density 0.004%

    No Known Activations