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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or exclamation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.21
     itſelf
    -1.07
     Efq
    -1.03
     themſelves
    -1.01
     houſe
    -0.98
     himſelf
    -0.95
     useRouter
    -0.94
     againſt
    -0.91
     Houſe
    -0.89
     Monfieur
    -0.87
    POSITIVE LOGITS
     Oh
    1.10
    Oh
    1.02
     oh
    0.93
    oh
    0.88
     OH
    0.83
    OH
    0.73
    toh
    0.73
     sweet
    0.70
     Edwards
    0.69
     Schia
    0.68
    Act Density 0.049%

    No Known Activations