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

    Neuronpedia

    INDEX
    Explanations

    indicators of hypocrisy in political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.51
    Cyfarwyddwr
    -0.49
     esternos
    -0.46
    RefNanny
    -0.43
     invokingState
    -0.41
    FieldOffsetTable
    -0.41
    AccessorTable
    -0.41
     reformas
    -0.40
    SharedCtor
    -0.40
    ToBounds
    -0.40
    POSITIVE LOGITS
     Hypo
    0.56
     hypo
    0.54
    hypo
    0.52
    Hypo
    0.52
     complaints
    0.50
     hypocrisy
    0.49
     pourtant
    0.49
     lip
    0.47
     complaining
    0.46
     complaint
    0.45
    Act Density 0.564%

    No Known Activations