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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison and contrasting ideas

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

    especially, particularly, even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    følgelig
    -0.72
    IContainer
    -0.63
    AutoScaleMode
    -0.59
    spesies
    -0.59
    %"),
    -0.57
     Paglinawan
    -0.56
     */;
    -0.55
    )()
    -0.54
    يسة
    -0.54
    %',
    -0.54
    POSITIVE LOGITS
     especially
    1.72
    Especially
    1.70
     Especially
    1.64
    especially
    1.55
     particularly
    1.31
     apalagi
    1.31
     ESPEC
    1.27
     Apalagi
    1.22
     especialmente
    1.22
     even
    1.20
    Act Density 0.155%

    No Known Activations