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

    Neuronpedia

    INDEX
    Explanations

    language related to psychological distress or damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esiz
    -0.16
    ikut
    -0.15
     Sole
    -0.14
    iffe
    -0.14
     sole
    -0.14
    æľ«
    -0.14
    edin
    -0.13
    anela
    -0.13
    éħ¸
    -0.13
    иÑģлов
    -0.13
    POSITIVE LOGITS
     overall
    0.35
    overall
    0.30
     Overall
    0.28
     certain
    0.28
     general
    0.27
    Overall
    0.26
    general
    0.25
     Certain
    0.23
    Certain
    0.21
     basic
    0.21
    Act Density 0.005%

    No Known Activations