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

    Neuronpedia

    INDEX
    Explanations

    politically and socially charged words and phrases related to current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     respons
    -0.84
     prec
    -0.80
     eleph
    -0.78
     manif
    -0.75
     wiser
    -0.73
     exha
    -0.72
     purs
    -0.71
    xual
    -0.70
     compulsory
    -0.70
     theirs
    -0.70
    POSITIVE LOGITS
    Posted
    1.36
    WASHINGTON
    1.32
    Abstract
    1.27
    Offline
    1.26
    Disclaimer
    1.26
    Details
    1.25
    Latest
    1.25
    TOR
    1.25
    Overview
    1.25
    Joined
    1.24
    Act Density 0.622%

    No Known Activations