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

    Neuronpedia

    INDEX
    Explanations

    words related to conditions and terms in agreements or contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dillon
    -0.18
    ottes
    -0.17
     Kraj
    -0.15
    /kernel
    -0.14
    hw
    -0.14
    islav
    -0.14
    et
    -0.14
    ysis
    -0.14
     Russo
    -0.14
     Shard
    -0.13
    POSITIVE LOGITS
    ë¬
    0.16
    unnable
    0.16
     bond
    0.15
    morgan
    0.15
    mant
    0.15
     hypoth
    0.14
    bate
    0.14
    nde
    0.14
    oard
    0.14
    -gnu
    0.14
    Act Density 0.004%

    No Known Activations