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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating accountability and responsibility, particularly in relation to law enforcement actions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.87
    ULAR
    -0.80
    ãĤ¼ãĤ¦ãĤ¹
    -0.76
    oodle
    -0.68
    Widget
    -0.66
    olves
    -0.65
    pecially
    -0.65
    MpServer
    -0.65
    arah
    -0.64
    ãĤ©
    -0.64
    POSITIVE LOGITS
     unlike
    1.16
     despite
    1.02
     there
    0.97
     according
    0.96
     contrary
    0.93
     although
    0.92
     owing
    0.90
     whereas
    0.88
     none
    0.87
     insofar
    0.87
    Act Density 0.167%

    No Known Activations