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

    Neuronpedia

    INDEX
    Explanations

    phrases related to getting rid of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal issues and the need for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tar
    -0.79
    rules
    -0.75
    pull
    -0.71
    doc
    -0.70
    rem
    -0.68
    drawn
    -0.67
    shi
    -0.67
    uld
    -0.65
     restraints
    -0.65
     sidx
    -0.64
    POSITIVE LOGITS
     coffers
    1.00
    abase
    0.91
     arenas
    0.85
     streets
    0.83
     entire
    0.82
     beaches
    0.79
     shelves
    0.79
     cities
    0.78
    selves
    0.78
     shores
    0.77
    Act Density 0.482%

    No Known Activations