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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    monetary values expressed in dollars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sed
    -0.74
     motions
    -0.73
     Puzz
    -0.72
     demol
    -0.70
     corrections
    -0.69
     Valent
    -0.69
     Gray
    -0.67
     motion
    -0.67
     interf
    -0.67
     Vid
    -0.66
    POSITIVE LOGITS
    100
    1.46
    1000
    1.40
    200
    1.38
    300
    1.36
    400
    1.35
    150
    1.35
    600
    1.32
    5000
    1.31
    500
    1.29
    250
    1.27
    Act Density 0.070%

    No Known Activations