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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obtaining or revealing truth and insightful information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     subprocess
    -0.58
     fubject
    -0.55
     otomatig
    -0.54
     ſtate
    -0.54
    "?>
    -0.54
     appearing
    -0.52
     itſelf
    -0.52
    keyDown
    -0.52
    rouge
    -0.52
     mouseY
    -0.52
    POSITIVE LOGITS
     ricev
    0.69
     Receive
    0.66
     mergeFrom
    0.66
    ActionCreators
    0.65
     receives
    0.63
     RECEIVE
    0.63
     receive
    0.62
     brunt
    0.61
    received
    0.60
     received
    0.59
    Act Density 0.299%

    No Known Activations