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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government actions and policies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Emin
    -0.78
    ï¸ı
    -0.75
    ï¸
    -0.74
     beads
    -0.72
    lasses
    -0.64
     Eps
    -0.61
    aston
    -0.61
     Candle
    -0.61
    lass
    -0.61
     Shards
    -0.60
    POSITIVE LOGITS
    sponsored
    1.00
    issued
    1.00
    administ
    0.95
    controlled
    0.93
    funded
    0.92
    imposed
    0.87
    funding
    0.84
    approved
    0.83
    paid
    0.82
    backed
    0.82
    Act Density 20.295%

    No Known Activations