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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or lack of awareness regarding actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufe
    -0.17
    ixin
    -0.15
    Ñİдж
    -0.14
    ÙĬÙģØ©
    -0.14
    usercontent
    -0.14
    ryn
    -0.14
    agos
    -0.14
    ãĤ¥
    -0.14
    ISMATCH
    -0.14
    utow
    -0.14
    POSITIVE LOGITS
    adas
    0.17
     correspond
    0.17
     ado
    0.17
    оÑĤи
    0.15
    缸
    0.15
     hierarchical
    0.14
     Westbrook
    0.14
    /fixtures
    0.14
     stability
    0.14
    obs
    0.14
    Act Density 0.128%

    No Known Activations