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

    Neuronpedia

    INDEX
    Explanations

    topics related to social issues and policy changes

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social issues and reforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ°
    -0.74
    rontal
    -0.66
    urat
    -0.64
    UAL
    -0.59
    canon
    -0.58
    xual
    -0.55
    idav
    -0.55
    aughs
    -0.53
    urai
    -0.52
    ysical
    -0.52
    POSITIVE LOGITS
     populations
    0.72
     hazards
    0.69
     protections
    0.66
     activities
    0.64
     harms
    0.62
     outcomes
    0.61
     havens
    0.61
     services
    0.60
     impacts
    0.60
     infrastructure
    0.60
    Act Density 0.876%

    No Known Activations