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

    Neuronpedia

    INDEX
    Explanations

    terms related to edges and their attributes

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

    edge of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ünster
    -0.42
    angliski
    -0.41
     !)
    -0.40
     Twitter
    -0.40
     Australian
    -0.39
     {}),
    -0.39
     Pizarro
    -0.39
    ')(
    -0.39
     professor
    -0.38
                  
    -0.38
    POSITIVE LOGITS
     edge
    2.33
     Edge
    2.16
    Edge
    2.08
    edge
    2.08
     EDGE
    1.95
    EDGE
    1.77
     edges
    1.70
     Edges
    1.63
    edges
    1.56
    Edges
    1.47
    Act Density 0.014%

    No Known Activations