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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thoughts or mental processes

    oai_token-act-pair · gpt-3.5-turbo

    references to mental and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Firm
    -0.65
     Suff
    -0.61
     MOD
    -0.60
     Tycoon
    -0.59
     ISS
    -0.59
     Mub
    -0.58
     Split
    -0.58
    inctions
    -0.56
     Pix
    -0.56
    ammy
    -0.56
    POSITIVE LOGITS
    steps
    0.87
    ails
    0.72
     selves
    0.68
    eks
    0.66
    stal
    0.65
     ancest
    0.65
     Nightmares
    0.62
    swing
    0.61
     doorstep
    0.61
     fireplace
    0.61
    Act Density 0.115%

    No Known Activations