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

    Neuronpedia

    INDEX
    Explanations

    instances of subjective modifiers indicating excessiveness or qualifications of qualities

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

    too followed by adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.45
    InitVars
    -0.44
    makeConstraints
    -0.43
     مشين
    -0.40
    AccessorTable
    -0.39
    //
    -0.38
    PageRoute
    -0.36
    MessageOf
    -0.36
    TestTools
    -0.35
    PostInfinity
    -0.35
    POSITIVE LOGITS
     too
    1.55
    too
    1.46
    Too
    1.41
     Too
    1.37
     TOO
    1.25
     demasiado
    1.16
    TOO
    1.11
     troppo
    1.06
     слишком
    1.00
     terlalu
    0.98
    Act Density 0.032%

    No Known Activations