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

    Neuronpedia

    INDEX
    Explanations

    phrases related to garment and product details

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affili
    -1.00
     education
    -0.81
     advis
    -0.80
     particip
    -0.80
     absentee
    -0.78
     boycot
    -0.78
     credential
    -0.77
     entitlement
    -0.77
     indebted
    -0.76
     publicly
    -0.75
    POSITIVE LOGITS
     Luckily
    1.25
     Also
    1.23
     Otherwise
    1.23
     Seems
    1.22
     Normally
    1.22
     Looks
    1.21
     Thankfully
    1.20
     However
    1.19
     Ideally
    1.18
     Usually
    1.17
    Act Density 0.347%

    No Known Activations