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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to scientific research and societal awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uru
    -0.15
     surviv
    -0.15
    viders
    -0.14
    437
    -0.14
    rita
    -0.14
     Alias
    -0.13
    lobber
    -0.13
    cola
    -0.13
     Compound
    -0.13
    otos
    -0.13
    POSITIVE LOGITS
     FEATURE
    0.14
    ÙĤب
    0.14
    OMPI
    0.14
    dao
    0.14
     Bett
    0.14
    òi
    0.14
     helf
    0.14
    bla
    0.13
    енÑĮ
    0.13
    ông
    0.13
    Act Density 0.028%

    No Known Activations