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

    Neuronpedia

    INDEX
    Explanations

    exclamations and personal expressions used in conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "you are" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tension
    -0.72
     blending
    -0.71
     scarcity
    -0.69
     succession
    -0.68
     alternating
    -0.68
     friction
    -0.66
     rotating
    -0.65
     isolation
    -0.65
     delegation
    -0.63
     utilization
    -0.62
    POSITIVE LOGITS
    mite
    1.05
    s
    0.99
    mean
    0.97
    ï¸ı
    0.96
    ng
    0.95
    med
    0.90
    st
    0.90
    t
    0.90
    tain
    0.89
    amaz
    0.88
    Act Density 0.169%

    No Known Activations