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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate embellishments or stylistic enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.89
     whoſe
    -0.88
     cauſe
    -0.87
     Anſ
    -0.86
     Theſe
    -0.85
     Monfieur
    -0.85
    ſelf
    -0.81
     Efq
    -0.80
     houſe
    -0.78
     anſ
    -0.77
    POSITIVE LOGITS
     tinge
    0.84
     emphasis
    0.80
     tinged
    0.71
     hint
    0.69
    rawDesc
    0.66
    TemporalType
    0.66
     hints
    0.65
     tint
    0.65
     bias
    0.64
     toques
    0.63
    Act Density 0.296%

    No Known Activations