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

    Neuronpedia

    INDEX
    Explanations

    specific patterns in dialogue or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.16
    ÏĢη
    -0.15
    ennent
    -0.14
    ilha
    -0.14
    اÙĦØ¥
    -0.14
    ì¶ľ
    -0.13
    é§
    -0.13
    Ùıس
    -0.13
    porto
    -0.13
     publish
    -0.13
    POSITIVE LOGITS
     request
    0.58
     requests
    0.54
    request
    0.47
    请æ±Ĥ
    0.47
     ask
    0.46
     requested
    0.46
    -request
    0.45
     asks
    0.45
     Request
    0.45
     demand
    0.45
    Act Density 0.014%

    No Known Activations