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

    Neuronpedia

    INDEX
    Explanations

    references to places of refuge or safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernel
    -0.18
    aign
    -0.17
    à¸²à¸ł
    -0.17
    chers
    -0.16
    æľĹ
    -0.15
    .touches
    -0.15
    annes
    -0.15
    ais
    -0.15
    ungal
    -0.14
    unct
    -0.14
    POSITIVE LOGITS
     shelter
    0.20
     seekers
    0.20
     Seek
    0.18
    mere
    0.17
     Shelter
    0.17
    belt
    0.17
     seeker
    0.17
    ECTOR
    0.16
    /source
    0.16
    -seeking
    0.16
    Act Density 0.035%

    No Known Activations