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

    Neuronpedia

    INDEX
    Explanations

    references to legal services and health-related claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    retch
    -0.17
    letcher
    -0.16
    uder
    -0.15
    ieren
    -0.15
    aption
    -0.14
    orp
    -0.14
     Tear
    -0.14
    nants
    -0.14
     Hemisphere
    -0.14
    íĥĢìĿ´
    -0.14
    POSITIVE LOGITS
     compensation
    0.23
     Compensation
    0.23
     injury
    0.20
     mes
    0.20
     Injury
    0.20
     Sokol
    0.19
    ntl
    0.18
     victim
    0.17
     injured
    0.17
     consumer
    0.17
    Act Density 0.184%

    No Known Activations