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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate addition or accumulation

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

    also finding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istoitu
    -0.65
     <=",
    -0.62
     otomatig
    -0.57
     beginnetje
    -0.53
    BASEPATH
    -0.53
     autorytatywna
    -0.52
     snippetHide
    -0.52
    /*
    -0.51
    Externí
    -0.50
     PeEnEo
    -0.49
    POSITIVE LOGITS
    💼
    0.38
    APIView
    0.37
     Elizabeth
    0.36
    :✨
    0.34
    RegressionTest
    0.34
    okay
    0.34
    gol
    0.33
    adell
    0.33
     كومونز
    0.33
    Elizabeth
    0.33
    Act Density 0.267%

    No Known Activations