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

    Neuronpedia

    INDEX
    Explanations

    terms related to political actions and policies

    oai_token-act-pair · gpt-3.5-turbo

    topics related to funding and legislative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vill
    -0.69
    Cooldown
    -0.65
     Jagu
    -0.60
    Parents
    -0.59
    iHUD
    -0.59
    Pitt
    -0.58
    Romney
    -0.58
    Pope
    -0.57
    Nusra
    -0.56
     poets
    -0.56
    POSITIVE LOGITS
     the
    0.92
     either
    0.87
     both
    0.80
     this
    0.79
     behalf
    0.78
     whichever
    0.72
    quartered
    0.69
     it
    0.67
    the
    0.66
     Entered
    0.61
    Act Density 0.627%

    No Known Activations