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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical information expressed in lists

    oai_token-act-pair · gpt-3.5-turbo

    discrete numbers and their associated context in a sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spir
    -0.82
     synerg
    -0.78
     intermedi
    -0.77
     regener
    -0.76
     sculpt
    -0.75
     tyres
    -0.75
     flared
    -0.73
     retard
    -0.73
     winding
    -0.72
     agon
    -0.72
    POSITIVE LOGITS
    1
    1.55
    âĢ¢
    1.54
    âĸł
    1.54
    First
    1.51
    âĻ¦
    1.49
    Firstly
    1.47
    Advertisements
    1.41
    FIR
    1.41
    Name
    1.41
    Names
    1.38
    Act Density 0.260%

    No Known Activations