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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversy and public discourse

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERG
    -0.71
    behind
    -0.67
    orrect
    -0.66
    arcity
    -0.65
     ahead
    -0.64
    pring
    -0.63
    Ec
    -0.60
     synonymous
    -0.60
     donors
    -0.59
     Ahead
    -0.57
    POSITIVE LOGITS
     microscope
    1.08
     guise
    0.96
     ausp
    0.90
     hood
    0.89
     radar
    0.86
     veil
    0.84
     scanner
    0.82
     jurisdiction
    0.81
     canopy
    0.81
     supervision
    0.81
    Act Density 0.056%

    No Known Activations