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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures or large numbers related to events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olds
    -0.15
    anzi
    -0.15
    GAN
    -0.14
    Gram
    -0.14
    (s
    -0.14
    501
    -0.13
    ORA
    -0.13
    enthal
    -0.13
     ÙĪÛĮÚ©ÛĮ
    -0.13
    amen
    -0.13
    POSITIVE LOGITS
     different
    0.26
    âĢ³
    0.24
    -plus
    0.22
    different
    0.21
     separate
    0.20
     (!
    0.20
    th
    0.20
    ê°ľìĿĺ
    0.19
     altogether
    0.19
     total
    0.19
    Act Density 0.186%

    No Known Activations