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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal hope or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ariConfig
    -0.45
    varargin
    -0.35
     gesteld
    -0.35
     Thur
    -0.34
    localized
    -0.34
     gezet
    -0.33
    ごちそうさまでした
    -0.33
     tilf
    -0.32
    puted
    -0.32
    果た
    -0.32
    POSITIVE LOGITS
     snippetHide
    0.69
     <>",
    0.63
    lilla
    0.57
    richTextPanel
    0.57
     ProtoMessage
    0.57
    writeField
    0.54
     CreateTagHelper
    0.53
    principalColumn
    0.51
    Aholisi
    0.50
    पया
    0.49
    Act Density 0.638%

    No Known Activations