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

    Neuronpedia

    INDEX
    Explanations

    contractions with "I am" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal sentiment or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     membr
    -0.74
     occurs
    -0.71
     Reduce
    -0.67
     mater
    -0.65
     Ensure
    -0.65
     emerges
    -0.64
     derives
    -0.64
     meets
    -0.64
     entails
    -0.63
     lasts
    -0.63
    POSITIVE LOGITS
     glad
    1.35
     gonna
    1.23
     thankful
    1.20
     hoping
    1.20
     sorry
    1.15
     guessing
    1.15
     grateful
    1.10
     afraid
    1.07
     sure
    1.04
     proud
    1.02
    Act Density 0.097%

    No Known Activations