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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "scope" in various contexts

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

    scope of context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trainer
    -0.47
     addNew
    -0.47
    -
    -0.45
    <bos>
    -0.45
    制造
    -0.45
     Fer
    -0.44
    arons
    -0.44
     trainers
    -0.44
    manufactured
    -0.44
     Herrmann
    -0.43
    POSITIVE LOGITS
    scope
    1.38
     Scope
    1.36
    Scope
    1.33
     scope
    1.33
     SCOPE
    1.31
    SCOPE
    1.21
     scopes
    1.01
    Scopes
    0.95
    scopes
    0.91
    cope
    0.91
    Act Density 0.010%

    No Known Activations