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

    Neuronpedia

    INDEX
    Explanations

    phrases that relate to perspective and context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é«ĺãģĦ
    -0.15
    usch
    -0.14
     Williamson
    -0.14
    ãģ«åIJij
    -0.14
     Photon
    -0.13
    ÑģÑĥÑĤ
    -0.13
     Zones
    -0.13
    lá
    -0.13
    ¾ç¤º
    -0.13
    056
    -0.13
    POSITIVE LOGITS
     context
    0.95
    context
    0.83
     Context
    0.78
    -context
    0.71
     CONTEXT
    0.69
    Context
    0.69
     contexto
    0.67
    _context
    0.66
     contexts
    0.66
    .context
    0.66
    Act Density 0.181%

    No Known Activations