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

    Neuronpedia

    INDEX
    Explanations

    references to different contexts or contextual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    usage of the word context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.46
     Anſ
    -0.46
    intelligence
    -0.46
    msgTypes
    -0.46
    Rolling
    -0.44
     Diſ
    -0.44
    MethodManager
    -0.43
    Surgical
    -0.43
    Intelligence
    -0.43
    rollable
    -0.42
    POSITIVE LOGITS
     contexts
    1.29
     contextos
    1.06
     context
    1.04
    contexts
    1.01
     Context
    0.99
     CONTEXT
    0.93
    context
    0.93
    Contexts
    0.93
     contexto
    0.92
     contexte
    0.88
    Act Density 0.006%

    No Known Activations