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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve sequential actions or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.45
     Revolución
    -0.41
     jScrollPane
    -0.41
    olm
    -0.40
    новништво
    -0.39
    ocyan
    -0.39
     autorytatywna
    -0.39
     river
    -0.37
    när
    -0.36
    cuno
    -0.36
    POSITIVE LOGITS
     afterwards
    0.51
     sonra
    0.47
     subsequent
    0.47
     then
    0.44
    esModule
    0.44
    HomeAsUpEnabled
    0.44
     Subsequent
    0.44
    yarnpkg
    0.43
     Afterwards
    0.43
    RectangleBorder
    0.43
    Act Density 1.121%

    No Known Activations