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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causing harm or danger

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the imposition of burdens or pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     experiences
    -0.77
    events
    -0.72
     matters
    -0.71
     revelations
    -0.71
    anism
    -0.70
     modes
    -0.69
     secrets
    -0.66
    projects
    -0.65
    anship
    -0.65
    settings
    -0.65
    POSITIVE LOGITS
     halt
    1.10
     lid
    1.09
     stop
    1.04
     moratorium
    1.03
     limit
    0.98
     disclaimer
    0.97
     spotlight
    0.97
     dent
    0.96
     ceiling
    0.96
     smile
    0.96
    Act Density 0.067%

    No Known Activations