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

    Neuronpedia

    INDEX
    Explanations

    dark-related imagery and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to dark imagery and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utable
    -0.80
    raltar
    -0.80
    kson
    -0.76
    llah
    -0.76
    ufact
    -0.75
    agine
    -0.73
    essors
    -0.72
    oples
    -0.72
    onent
    -0.72
    yip
    -0.70
    POSITIVE LOGITS
    ening
    1.23
    ened
    1.08
     recess
    0.92
    horse
    0.89
    moon
    0.88
     clouds
    0.87
     gray
    0.85
    dark
    0.85
     brown
    0.83
     grey
    0.83
    Act Density 0.030%

    No Known Activations