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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Phil"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Phil" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.94
    tenance
    -0.80
    DERR
    -0.77
    yrinth
    -0.76
    Demand
    -0.75
    erers
    -0.68
    erness
    -0.67
    FACE
    -0.66
    CONCLUS
    -0.66
    GGGG
    -0.65
    POSITIVE LOGITS
    anthrop
    1.43
    istine
    1.32
    andering
    1.08
    oton
    1.07
    adel
    1.06
    harm
    1.02
    orio
    1.00
    onen
    1.00
    ophe
    1.00
    oshenko
    0.99
    Act Density 0.013%

    No Known Activations