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

    Neuronpedia

    INDEX
    Explanations

    numerical representations, likely related to quantitative data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iniz
    -0.16
    inz
    -0.16
    dad
    -0.16
    dal
    -0.15
    elf
    -0.15
    ess
    -0.14
    places
    -0.14
    ed
    -0.14
    ell
    -0.14
    esh
    -0.14
    POSITIVE LOGITS
    s
    0.25
    ÏĤ
    0.17
    sik
    0.17
    st
    0.16
    sak
    0.16
    ãĥ³ãĥĸ
    0.15
    ë²Ī
    0.15
    sip
    0.15
    ska
    0.15
    urtle
    0.15
    Act Density 0.125%

    No Known Activations