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

    Neuronpedia

    INDEX
    Explanations

    words related to academic and government institutions and agriculture

    oai_token-act-pair · gpt-3.5-turbo

    terms related to animal welfare and agricultural assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.83
    theless
    -0.78
    olson
    -0.74
    ardless
    -0.73
    early
    -0.71
    umbers
    -0.71
    comed
    -0.70
    itely
    -0.69
     externalToEVAOnly
    -0.68
    aned
    -0.67
    POSITIVE LOGITS
     Complex
    1.07
     Areas
    1.02
     Solutions
    1.02
     Units
    1.01
     Unit
    1.00
     Initiative
    1.00
     Association
    0.98
     Solution
    0.96
     Controller
    0.95
     Control
    0.95
    Act Density 0.069%

    No Known Activations