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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical walls or barriers

    oai_token-act-pair · gpt-3.5-turbo

    references to protective barriers or restrictions, particularly in digital contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amate
    -0.67
    cess
    -0.66
    heny
    -0.65
    veh
    -0.65
     costly
    -0.64
    Gene
    -0.59
    igure
    -0.58
    emi
    -0.58
     expensive
    -0.58
    sb
    -0.58
    POSITIVE LOGITS
    abies
    1.17
    papers
    1.06
    paper
    0.99
    wall
    0.91
     wallpaper
    0.84
    aby
    0.80
    stones
    0.79
    igans
    0.77
    nesday
    0.74
    iard
    0.68
    Act Density 0.016%

    No Known Activations