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

    Neuronpedia

    INDEX
    Explanations

    locations and events related to crimes or violence

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving violence or danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ploma
    -0.80
     substit
    -0.70
    maxwell
    -0.69
    phabet
    -0.69
     mastered
    -0.68
    anguage
    -0.68
    papers
    -0.67
    ministic
    -0.66
    ONEY
    -0.66
    peat
    -0.66
    POSITIVE LOGITS
     intersection
    0.96
     courthouse
    0.82
     mall
    0.81
     plaza
    0.81
     Augusta
    0.79
     downtown
    0.79
     premises
    0.77
     Plaza
    0.75
    auder
    0.73
     campus
    0.73
    Act Density 0.595%

    No Known Activations