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

    Neuronpedia

    INDEX
    Explanations

    terms related to competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atics
    -0.21
    okable
    -0.19
    sd
    -0.16
    kest
    -0.16
    aires
    -0.16
    ses
    -0.15
    ugin
    -0.15
     Dane
    -0.15
    ERING
    -0.15
    525
    -0.15
    POSITIVE LOGITS
    itors
    0.33
    itor
    0.32
    encies
    0.30
    itive
    0.30
    ITOR
    0.29
    itions
    0.27
    izione
    0.24
    ITIVE
    0.23
    ición
    0.23
    compet
    0.22
    Act Density 0.007%

    No Known Activations