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

    Neuronpedia

    INDEX
    Explanations

    words related with criticism and controversy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uate
    -0.91
     inhibition
    -0.67
    uated
    -0.66
     unpre
    -0.65
     sucker
    -0.64
     susceptibility
    -0.61
    inates
    -0.61
     gratification
    -0.61
    arial
    -0.61
     psy
    -0.60
    POSITIVE LOGITS
    ITNESS
    1.24
    atts
    1.21
    elcome
    1.19
    restling
    1.19
    nesday
    1.17
    edge
    1.13
    atson
    1.11
    orthy
    1.10
    isdom
    1.10
    ashington
    1.10
    Act Density 1.627%

    No Known Activations