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

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions and approvals in formal settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efa
    -0.16
    mai
    -0.14
    owl
    -0.14
    arp
    -0.14
    omat
    -0.13
    693
    -0.13
    è¨
    -0.13
    992
    -0.13
    pll
    -0.13
    lue
    -0.13
    POSITIVE LOGITS
     approval
    0.34
     prior
    0.33
     written
    0.32
     permission
    0.30
     proper
    0.27
    written
    0.27
    prior
    0.27
     explicit
    0.25
     consultation
    0.25
    approval
    0.25
    Act Density 0.224%

    No Known Activations