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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "inspired" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilde
    -0.18
    essa
    -0.17
    ÏĦαν
    -0.16
    odzi
    -0.16
    liness
    -0.16
    stile
    -0.15
    gie
    -0.15
    зв
    -0.14
    ppy
    -0.14
    ม
    -0.14
    POSITIVE LOGITS
    zia
    0.19
    strup
    0.16
     awe
    0.15
    llum
    0.14
    zzo
    0.14
    fruit
    0.14
     quot
    0.14
    needle
    0.14
    Seat
    0.14
    lesi
    0.13
    Act Density 0.022%

    No Known Activations