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

    Neuronpedia

    INDEX
    Explanations

    elements related to formal procedural language or structured lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WARRANT
    -0.15
    hra
    -0.14
     UNU
    -0.14
     Moines
    -0.14
    моÑĤ
    -0.14
     trout
    -0.14
     Students
    -0.14
    oil
    -0.14
     repent
    -0.13
    Aws
    -0.13
    POSITIVE LOGITS
     Celebrity
    0.39
     Carnival
    0.29
     Edge
    0.28
     Cruise
    0.27
     cruise
    0.25
     celebrity
    0.25
     EDGE
    0.24
    Celebr
    0.24
     cruis
    0.24
     Royal
    0.23
    Act Density 0.002%

    No Known Activations