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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with edges and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alars
    -0.16
    alc
    -0.15
    é¼
    -0.14
     Nich
    -0.14
    uno
    -0.14
    ืà¸Ńà¸ģ
    -0.14
     Blick
    -0.14
    yny
    -0.13
    InBackground
    -0.13
    درس
    -0.13
    POSITIVE LOGITS
     edge
    0.66
     edges
    0.60
     Ed
    0.53
    -edge
    0.52
     Edge
    0.51
     ed
    0.51
    edge
    0.50
    .edge
    0.49
    _edge
    0.49
    Edge
    0.48
    Act Density 0.098%

    No Known Activations