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

    Neuronpedia

    INDEX
    Explanations

    words that signal uncertainty or emotional distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑĸз
    -0.17
    acci
    -0.16
    iones
    -0.16
    ç·Ĵ
    -0.15
    Ī
    -0.15
    acle
    -0.15
     Proud
    -0.15
    IRD
    -0.14
    icont
    -0.14
    ION
    -0.14
    POSITIVE LOGITS
    subcategory
    0.15
    alian
    0.15
    otron
    0.14
    WF
    0.14
    gate
    0.14
    eria
    0.14
     conv
    0.14
    iaux
    0.14
    bour
    0.14
    .sdk
    0.14
    Act Density 0.001%

    No Known Activations