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

    Neuronpedia

    INDEX
    Explanations

    references to monetary amounts and deals

    oai_token-act-pair · gpt-3.5-turbo

    monetary pledges and financial contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cod
    -0.72
     gon
    -0.71
     nos
    -0.69
     resemb
    -0.65
     orig
    -0.63
     Riley
    -0.63
     typ
    -0.63
     disse
    -0.63
     ops
    -0.63
    ococ
    -0.62
    POSITIVE LOGITS
    1000
    1.42
    200
    1.40
    100
    1.40
    200000
    1.34
    300
    1.33
    150
    1.33
    1600
    1.30
    800
    1.29
    1200
    1.29
    1500
    1.29
    Act Density 0.252%

    No Known Activations