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

    Neuronpedia

    INDEX
    Explanations

    words related to public, political, or personal matters and responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    references to personal, national, or global responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.76
    iple
    -0.74
    ARP
    -0.73
    kson
    -0.72
    athing
    -0.72
    esville
    -0.72
    imates
    -0.71
    âķIJ
    -0.71
    oug
    -0.70
    DES
    -0.69
    POSITIVE LOGITS
     affairs
    1.19
    afety
    0.86
    matter
    0.78
    hip
    0.76
     matters
    0.76
     oriented
    0.71
     enqu
    0.68
    manship
    0.67
    mith
    0.67
    chool
    0.67
    Act Density 0.016%

    No Known Activations