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

    Neuronpedia

    INDEX
    Explanations

    references to hypocrisy in political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.87
     purpoſe
    -0.75
     ſtate
    -0.70
     ſte
    -0.70
    numerusform
    -0.69
     Reſ
    -0.68
     houſe
    -0.67
    DebuggerNonUser
    -0.65
     Anſ
    -0.65
     ſta
    -0.64
    POSITIVE LOGITS
    WithIOException
    0.57
    LABEL
    0.51
    TabIndex
    0.48
    ActivityCompat
    0.45
    ValueGenerated
    0.45
    gazette
    0.45
     when
    0.45
    ugc
    0.44
     sou
    0.44
    าศ
    0.44
    Act Density 0.339%

    No Known Activations