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

    Neuronpedia

    INDEX
    Explanations

    references to prison settings and dynamics involving inmates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MARKETS
    -0.69
    AnchorTagHelper
    -0.59
    PerformLayout
    -0.59
    InitVars
    -0.56
     markets
    -0.53
    consulté
    -0.53
     mercados
    -0.53
    Markets
    -0.52
     vó
    -0.52
    PAIGN
    -0.51
    POSITIVE LOGITS
     prison
    0.84
     Prison
    0.81
     inmates
    0.79
     inmate
    0.78
     prisons
    0.73
    Prison
    0.72
     facility
    0.72
     Correctional
    0.70
    prison
    0.70
     incarceration
    0.69
    Act Density 0.505%

    No Known Activations