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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arter
    -0.15
    orer
    -0.15
    ara
    -0.14
     everlasting
    -0.13
    veis
    -0.13
     proper
    -0.13
    porte
    -0.13
    лини
    -0.13
    ä¾ĭ
    -0.13
    wers
    -0.13
    POSITIVE LOGITS
    uling
    0.16
    uetype
    0.15
    anje
    0.14
    astle
    0.14
    bane
    0.14
    ença
    0.14
    ì¼Ģ
    0.14
    INVAL
    0.14
    ystal
    0.13
    umba
    0.13
    Act Density 0.101%

    No Known Activations