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

    Neuronpedia

    INDEX
    Explanations

    words related to social systems or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to structural or political frameworks within society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUS
    -0.64
    eor
    -0.60
    rolet
    -0.60
    oller
    -0.60
    stall
    -0.60
    ega
    -0.59
    ondo
    -0.58
    ainer
    -0.58
    OTAL
    -0.57
    rol
    -0.56
    POSITIVE LOGITS
     opposed
    1.11
    pects
    1.09
    ylum
    1.07
    pires
    1.07
     well
    1.02
    pired
    1.00
    cription
    1.00
     evidenced
    1.00
    bestos
    0.98
    criptions
    0.92
    Act Density 0.245%

    No Known Activations