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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and contractual terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alla
    -0.17
    eyer
    -0.15
     revers
    -0.14
     vere
    -0.14
     dro
    -0.14
     baz
    -0.14
    appers
    -0.13
     dm
    -0.13
     Cherry
    -0.13
    aya
    -0.13
    POSITIVE LOGITS
     purposes
    0.36
     purpose
    0.26
     PURPOSE
    0.21
     reasons
    0.19
    purpose
    0.18
    pur
    0.17
    iel
    0.17
     Purpose
    0.17
     profit
    0.15
    -purpose
    0.15
    Act Density 0.132%

    No Known Activations