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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical or numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.18
    loff
    -0.17
    leck
    -0.16
    eyse
    -0.15
    ż
    -0.15
    wards
    -0.14
    ollapsed
    -0.14
    kili
    -0.14
    liv
    -0.14
    ãģķãĤī
    -0.14
    POSITIVE LOGITS
     Orr
    0.21
    amera
    0.14
    omorphic
    0.14
    ofile
    0.14
    acci
    0.14
    δή
    0.14
    pname
    0.13
     rencont
    0.13
     Copyright
    0.13
    umar
    0.13
    Act Density 0.405%

    No Known Activations