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

    Neuronpedia

    INDEX
    Explanations

    references to migration, asylum-seeking, and safety in the context of refugees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    native
    -0.07
    aln
    -0.07
    ead
    -0.07
    aea
    -0.06
     consort
    -0.06
    heed
    -0.06
    onn
    -0.06
    Progress
    -0.06
    alom
    -0.06
    _FAULT
    -0.06
    POSITIVE LOGITS
     sympathetic
    0.08
     safe
    0.07
    SAFE
    0.07
    моÑĢ
    0.07
     escape
    0.07
     safer
    0.07
     safety
    0.06
    629
    0.06
    safe
    0.06
     nearby
    0.06
    Act Density 0.021%

    No Known Activations