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

    Neuronpedia

    INDEX
    Explanations

    notable mentions of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to different media outlets or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istries
    -0.69
    rontal
    -0.69
    estern
    -0.64
     INCLUD
    -0.63
    rang
    -0.63
    emate
    -0.62
    ashtra
    -0.61
    animate
    -0.60
    lux
    -0.60
    existence
    -0.59
    POSITIVE LOGITS
    terday
    0.75
    :[
    0.71
    iHUD
    0.70
    ":[
    0.69
     (),
    0.68
     aptly
    0.66
    :{
    0.66
     succinct
    0.63
     elsewhere
    0.63
     eloqu
    0.62
    Act Density 0.109%

    No Known Activations