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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions of receiving or obtaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.12
     ſtate
    -0.97
     purpoſe
    -0.96
     myſelf
    -0.93
     Trix
    -0.88
     themſelves
    -0.87
     neceff
    -0.84
    setVerticalGroup
    -0.83
     reaſon
    -0.81
     leſs
    -0.80
    POSITIVE LOGITS
     get
    1.50
     gets
    1.47
     got
    1.44
    Gets
    1.36
     getting
    1.34
     gotten
    1.34
     Gets
    1.25
     GETS
    1.25
     Get
    1.22
    Getting
    1.19
    Act Density 0.077%

    No Known Activations