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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and controversies

    oai_token-act-pair · gpt-3.5-turbo

    connections to various issues related to social inequality and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uct
    -0.75
    umbn
    -0.69
    escription
    -0.67
    Optional
    -0.66
    76561
    -0.62
    owered
    -0.62
     Username
    -0.60
    skin
    -0.60
     cuff
    -0.59
    EED
    -0.59
    POSITIVE LOGITS
     deserves
    1.18
     certainly
    1.13
     consequently
    1.10
     indeed
    1.09
     hence
    1.06
     rightfully
    1.06
     particularly
    1.03
     exacerbated
    1.01
     therein
    1.00
     underscores
    1.00
    Act Density 0.267%

    No Known Activations