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

    Neuronpedia

    INDEX
    Explanations

    words related to radioactive materials and incidents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -1.02
     PsyNet
    -0.80
    nee
    -0.76
    à©
    -0.72
    things
    -0.71
    ãĥ¯ãĥ³
    -0.70
    abases
    -0.69
    zee
    -0.69
    hetically
    -0.67
    stories
    -0.64
    POSITIVE LOGITS
     tremend
    1.27
     chloride
    0.93
     oxide
    0.80
    osate
    0.78
     dioxide
    0.74
     trem
    0.72
     arsen
    0.70
    s
    0.69
    esis
    0.67
    eus
    0.66
    Act Density 8.032%

    No Known Activations