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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'golden'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "golden"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.76
    lov
    -0.73
    hani
    -0.73
    Lay
    -0.70
    chens
    -0.69
     Simulator
    -0.67
    went
    -0.67
    ktop
    -0.67
    ciplinary
    -0.67
    utsu
    -0.66
    POSITIVE LOGITS
     maiden
    0.94
     shimmer
    0.88
     brown
    0.86
     glow
    0.86
     parachute
    0.86
     calf
    0.86
     parach
    0.82
     olive
    0.81
     retri
    0.79
     coloured
    0.79
    Act Density 0.026%

    No Known Activations