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

    Neuronpedia

    INDEX
    Explanations

    references to the speaker's personal experiences and thoughts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I have" followed by various nouns or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rift
    -0.65
    icking
    -0.64
    ipping
    -0.63
    osion
    -0.62
    eem
    -0.62
    allows
    -0.60
    oppable
    -0.58
    artney
    -0.58
    pport
    -0.57
    weed
    -0.56
    POSITIVE LOGITS
     been
    1.10
     heard
    1.05
     watched
    1.01
     noticed
    1.00
     seen
    1.00
     listened
    0.98
     personally
    0.98
     myself
    0.97
     NEVER
    0.94
     witnessed
    0.94
    Act Density 0.130%

    No Known Activations