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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.30
     rul
    -0.27
     territ
    -0.26
     Azerb
    -0.24
     conclud
    -0.23
     furthermore
    -0.23
    enegger
    -0.22
     moreover
    -0.22
     horizont
    -0.21
     manif
    -0.21
    POSITIVE LOGITS
    ratom
    0.25
    taboola
    0.20
    osures
    0.19
    SI
    0.19
    IGHTS
    0.18
    ANE
    0.18
    yrights
    0.18
    AK
    0.17
    OFF
    0.17
    ISC
    0.17
    Act Density 5.534%

    No Known Activations