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

    Neuronpedia

    INDEX
    Explanations

    expressions related to past events or reminiscing

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to nostalgia or past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.72
     externalToEVAOnly
    -0.70
    ivari
    -0.68
     sqor
    -0.68
    ictional
    -0.67
    rored
    -0.63
    bourg
    -0.62
    umbn
    -0.62
    ACTED
    -0.61
    icide
    -0.60
    POSITIVE LOGITS
    dream
    1.30
    nings
    0.95
    lights
    0.90
    stal
    0.76
    TON
    0.75
    motion
    0.72
    light
    0.71
    life
    0.70
    mar
    0.68
    kos
    0.67
    Act Density 0.046%

    No Known Activations