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

    Neuronpedia

    INDEX
    Explanations

    JavaScript if conditions and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    statements involving equality and comparison operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anto
    -0.76
    wana
    -0.75
    inburgh
    -0.74
    asca
    -0.73
    ugu
    -0.72
    oshop
    -0.72
    lections
    -0.71
    amps
    -0.69
    eli
    -0.69
    owan
    -0.69
    POSITIVE LOGITS
     null
    1.04
    ==
    0.98
     undefined
    0.96
     NULL
    0.87
     ==
    0.86
     ===
    0.86
     nil
    0.86
     !
    0.78
    null
    0.76
     eq
    0.74
    Act Density 0.024%

    No Known Activations