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

    Neuronpedia

    INDEX
    Explanations

    references to childhood

    oai_token-act-pair · gpt-3.5-turbo

    references to childhood experiences or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioxide
    -0.88
    andum
    -0.81
    abase
    -0.78
    oples
    -0.77
     lawy
    -0.76
    nant
    -0.71
    abases
    -0.70
    tical
    -0.70
    aceous
    -0.70
    pez
    -0.70
    POSITIVE LOGITS
     leukemia
    0.88
     memories
    0.86
     Memories
    0.77
     è£ıè
    0.77
     Childhood
    0.76
    ishly
    0.75
    ULT
    0.73
    stones
    0.73
     innocence
    0.72
    arten
    0.71
    Act Density 0.041%

    No Known Activations