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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or titles within a specific context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ourt
    -0.98
     Mehran
    -0.84
    hovah
    -0.80
    olis
    -0.79
    asus
    -0.78
    eled
    -0.77
     burgl
    -0.77
    ainted
    -0.74
    eny
    -0.74
     rents
    -0.74
    POSITIVE LOGITS
    stood
    1.20
    gaard
    1.18
    theless
    1.14
    stall
    1.13
    fulness
    1.13
    LAND
    1.10
    lich
    1.10
    hood
    1.08
    ground
    1.05
    stand
    1.05
    Act Density 1.123%

    No Known Activations