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

    Neuronpedia

    INDEX
    Explanations

    phrases or references that indicate possession or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uca
    -0.86
    fter
    -0.81
    vale
    -0.80
    Depth
    -0.78
    pring
    -0.77
    istan
    -0.75
    jad
    -0.73
    acus
    -0.72
    ibe
    -0.71
    ebus
    -0.71
    POSITIVE LOGITS
     acron
    1.02
     ailments
    1.00
     accomplishments
    1.00
     goodies
    0.98
     excuses
    0.98
     sorts
    0.96
     disparate
    0.92
     possibilities
    0.90
     achievements
    0.88
     grievances
    0.87
    Act Density 0.068%

    No Known Activations