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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing the word "dark"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "dark."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utable
    -0.81
    ufact
    -0.81
    oples
    -0.80
    llah
    -0.80
    raltar
    -0.77
    essors
    -0.75
    iphate
    -0.75
     Fas
    -0.74
    agine
    -0.73
    onent
    -0.71
    POSITIVE LOGITS
    ening
    1.15
    ened
    1.03
    moon
    0.88
     recess
    0.86
     brown
    0.83
    horse
    0.83
    ener
    0.82
    lit
    0.82
     clouds
    0.82
     grey
    0.82
    Act Density 0.023%

    No Known Activations