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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "am"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I am" followed by various personal statements or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externalToEVAOnly
    -0.69
     Gap
    -0.68
     occurs
    -0.65
     lasts
    -0.65
     entails
    -0.65
     Colleges
    -0.64
     hatch
    -0.63
     Tactics
    -0.63
     achieves
    -0.62
     fails
    -0.62
    POSITIVE LOGITS
     glad
    1.14
     thankful
    1.12
     grateful
    1.04
    azon
    0.98
     fortunate
    0.96
     proud
    0.94
     honored
    0.92
     amazed
    0.91
     myself
    0.90
     delighted
    0.90
    Act Density 0.096%

    No Known Activations