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

    Neuronpedia

    INDEX
    Explanations

    versions and software updates

    oai_token-act-pair · gpt-3.5-turbo

    decimal numbers and versioning information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thr
    -0.66
     deduct
    -0.65
     funer
    -0.65
     comedian
    -0.61
     divide
    -0.60
     mathematician
    -0.60
     purse
    -0.60
     carpet
    -0.60
     gull
    -0.60
     undermin
    -0.59
    POSITIVE LOGITS
    0
    1.56
    5
    1.30
    6
    1.22
    4
    1.20
    3
    1.19
    7
    1.17
    04
    1.15
    8
    1.15
    9
    1.15
    x
    1.11
    Act Density 0.044%

    No Known Activations