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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating context and relevance in discussions or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cassidy
    -0.16
     Commod
    -0.16
     Cyrus
    -0.16
    egra
    -0.16
    usch
    -0.15
     Companion
    -0.15
     Clarence
    -0.15
    akit
    -0.15
     Curl
    -0.15
    ichel
    -0.15
    POSITIVE LOGITS
     context
    0.84
    context
    0.73
     Context
    0.66
    .context
    0.63
    -context
    0.62
     contexto
    0.61
    _context
    0.61
     contexts
    0.60
    Context
    0.60
    	context
    0.58
    Act Density 0.118%

    No Known Activations