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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusion or removal from various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     }{@
    -0.50
    fjspx
    -0.45
     far
    -0.44
    tudiant
    -0.41
     kèm
    -0.41
     sưu
    -0.40
    GetKey
    -0.39
    -0.38
     tùy
    -0.36
    してくれる
    -0.36
    POSITIVE LOGITS
    RegressionTest
    0.60
    makeText
    0.58
    addTo
    0.56
    listdir
    0.55
     khỏi
    0.54
    removeFrom
    0.53
     addTo
    0.52
     removeFrom
    0.52
    localctx
    0.50
    rizona
    0.48
    Act Density 0.634%

    No Known Activations