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

    Neuronpedia

    INDEX
    Explanations

    words related to social issues

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.92
    20439
    -0.80
    urat
    -0.76
    ilts
    -0.74
     Ridge
    -0.73
     Blossom
    -0.66
    ucket
    -0.65
    butt
    -0.65
    tto
    -0.64
    sterdam
    -0.64
    POSITIVE LOGITS
    izing
    1.02
    ization
    1.01
     cohesion
    0.95
    ized
    0.95
    istic
    0.94
     norms
    0.93
     interaction
    0.91
     networking
    0.91
    ize
    0.90
     sciences
    0.89
    Act Density 0.025%

    No Known Activations