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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and activism

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.96
    20439
    -0.75
    urat
    -0.72
    ilts
    -0.71
    1001
    -0.70
     Ridge
    -0.70
    ARDS
    -0.69
    peed
    -0.67
     Blazing
    -0.66
    zzle
    -0.66
    POSITIVE LOGITS
    izing
    0.99
    ized
    0.97
    istic
    0.96
    ization
    0.95
     cohesion
    0.89
     norms
    0.88
     democr
    0.85
     welfare
    0.84
     sciences
    0.82
     interaction
    0.82
    Act Density 0.029%

    No Known Activations