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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and definite articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cially
    -0.82
    thood
    -0.77
    bourg
    -0.77
    cial
    -0.71
    humans
    -0.70
    Cash
    -0.70
    Leod
    -0.69
    adin
    -0.68
    Boost
    -0.68
    Europe
    -0.68
    POSITIVE LOGITS
     doorway
    1.18
     remainder
    1.09
     nearest
    1.09
     ceiling
    1.08
     horizon
    1.08
     entirety
    1.05
     hallway
    1.02
     slightest
    1.02
     fireplace
    1.00
     darkness
    0.99
    Act Density 0.365%

    No Known Activations