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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and procedural attributes concerning detention and immigration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tros
    -0.44
    utta
    -0.40
    st
    -0.40
     сту
    -0.40
    ish
    -0.39
    dist
    -0.38
     dre
    -0.37
     Ehr
    -0.37
    枕
    -0.37
     лу
    -0.37
    POSITIVE LOGITS
    SBATCH
    1.00
     granted
    0.87
     Efq
    0.82
     permits
    0.77
     déliv
    0.77
     granting
    0.76
     חיצוניים
    0.76
    GRANTED
    0.76
    Портали
    0.76
    permit
    0.74
    Act Density 0.511%

    No Known Activations