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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experiences and perspectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to experiences and reflections on personal history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GET
    -0.68
     Hide
    -0.63
     poses
    -0.62
     Mane
    -0.61
     demands
    -0.61
     boast
    -0.61
     rumours
    -0.60
     scissors
    -0.60
    #$
    -0.60
     Haram
    -0.59
    POSITIVE LOGITS
     firsthand
    1.13
     experien
    0.96
     experience
    0.96
     intimately
    0.90
     researching
    0.90
    exper
    0.86
     anecd
    0.84
     myself
    0.83
     immersed
    0.81
     familiarity
    0.81
    Act Density 0.486%

    No Known Activations