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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -0.88
    -0.86
     Efq
    -0.82
     Reſ
    -0.79
     myſelf
    -0.79
     Monfieur
    -0.79
     whoſe
    -0.78
    soever
    -0.77
     Majefty
    -0.77
    ſelves
    -0.75
    POSITIVE LOGITS
    GEBURTSDATUM
    0.51
     "..\..\..\
    0.47
    casual
    0.45
    ⓧ
    0.43
    .
    0.42
     ar
    0.42
     casual
    0.41
    gameserver
    0.41
     ch
    0.41
    ServiceModel
    0.41
    Act Density 0.512%

    No Known Activations