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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and startups

    oai_token-act-pair · gpt-3.5-turbo

    instances of repeated characters or emojis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tunis
    -0.71
     Paras
    -0.67
     Manhattan
    -0.62
     Tid
    -0.61
     Opera
    -0.61
     NYC
    -0.60
     Mansion
    -0.60
     Niet
    -0.60
     paras
    -0.58
     Palest
    -0.58
    POSITIVE LOGITS
    ı
    1.35
    ¬
    1.26
    į
    1.26
    Ń
    1.23
    ĸ
    1.21
    £
    1.16
    Ī
    1.15
    «
    1.15
    ħ
    1.13
    ¤
    1.13
    Act Density 0.065%

    No Known Activations