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

    Neuronpedia

    INDEX
    Explanations

    significant events or issues related to various countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to historical and contemporary political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ellipt
    -0.64
     definite
    -0.62
     caveat
    -0.60
     chang
    -0.59
     lighter
    -0.58
     extras
    -0.57
     directional
    -0.57
    oret
    -0.57
     redeem
    -0.57
     collaps
    -0.56
    POSITIVE LOGITS
     violates
    0.92
    utterstock
    0.88
    AFP
    0.80
     threatens
    0.80
     alleges
    0.78
    poses
    0.77
     perpetrated
    0.77
     undermines
    0.75
    ."[
    0.74
     culminated
    0.73
    Act Density 0.559%

    No Known Activations