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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals named Philip

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name Philip

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DERR
    -0.81
    yrinth
    -0.77
    eer
    -0.77
    bnb
    -0.73
    LOAD
    -0.70
    hips
    -0.67
    ipeg
    -0.64
    REAM
    -0.64
    system
    -0.63
    Ranked
    -0.63
    POSITIVE LOGITS
    anthrop
    0.85
     Morris
    0.82
     Randolph
    0.81
    entric
    0.77
    osate
    0.75
    son
    0.74
    istine
    0.73
     Seymour
    0.72
    opol
    0.70
     Hammond
    0.70
    Act Density 0.009%

    No Known Activations