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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to spatial positioning or orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyen
    -0.16
    stateParams
    -0.15
    [$_
    -0.15
    ÐĴС
    -0.14
    odu
    -0.14
    amment
    -0.14
    ายà¸Ļ
    -0.14
    .predicate
    -0.14
    ÑĢован
    -0.14
    ãĤ·ãĥ§ãĥ³
    -0.14
    POSITIVE LOGITS
    wards
    0.20
    /back
    0.20
    side
    0.19
     behind
    0.18
    ward
    0.17
    most
    0.16
    -most
    0.15
     Teh
    0.15
    ermann
    0.14
    er
    0.14
    Act Density 0.072%

    No Known Activations