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

    Neuronpedia

    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal reflections or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coverage
    -0.78
     pestic
    -0.71
     Workers
    -0.71
     Poster
    -0.70
     Officials
    -0.69
     Vest
    -0.67
     Protective
    -0.65
     ILCS
    -0.64
    «ĺ
    -0.63
     Verify
    -0.63
    POSITIVE LOGITS
     seemed
    1.16
     fascinated
    1.16
     intrigued
    1.08
     bothered
    1.08
     reminded
    1.08
     dawn
    1.06
     bothers
    1.05
     sucked
    1.03
     annoy
    1.02
     myself
    1.02
    Act Density 0.385%

    No Known Activations