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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or concepts indicating similarity or sameness

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

    the word "same"

    np_acts-logits-general · gemini-2.0-flash

    exact sameness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apalagi
    -0.60
     actualidad
    -0.49
     particolarmente
    -0.49
     especialmente
    -0.48
    seamnă
    -0.46
     särskilt
    -0.45
     MenuView
    -0.45
     siguientes
    -0.44
    #__
    -0.44
     propio
    -0.44
    POSITIVE LOGITS
     exact
    1.51
     thing
    1.23
    exact
    1.21
     Exact
    1.18
     EXACT
    1.15
    Exact
    0.96
     amount
    0.94
    EXACT
    0.93
     kind
    0.87
     THING
    0.87
    Act Density 0.129%

    No Known Activations