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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to refugees and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.17
    neh
    -0.16
     çŁ
    -0.15
    ifo
    -0.14
     Sachs
    -0.14
    quiv
    -0.14
    apan
    -0.14
    Ĥ¹
    -0.14
    gra
    -0.14
     Mahar
    -0.13
    POSITIVE LOGITS
    ess
    0.18
    OLON
    0.16
    orners
    0.15
    Å¡il
    0.15
    eron
    0.15
    enic
    0.15
    opoulos
    0.14
    osi
    0.14
    inalg
    0.14
    /ref
    0.14
    Act Density 0.009%

    No Known Activations