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

    Neuronpedia

    INDEX
    Explanations

    words related to scrutiny and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ach
    -0.18
    ucci
    -0.16
    лава
    -0.15
    aida
    -0.14
    rale
    -0.14
     Continental
    -0.14
    FOUND
    -0.14
    leness
    -0.13
    dings
    -0.13
    eggies
    -0.13
    POSITIVE LOGITS
    ing
    0.28
    ed
    0.18
    amespace
    0.15
    ़र
    0.15
    ning
    0.14
    391
    0.14
    ging
    0.13
    bing
    0.13
    ming
    0.13
    \Collections
    0.13
    Act Density 0.146%

    No Known Activations