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

    Neuronpedia

    INDEX
    Explanations

    general terms or concepts related to classification or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¡ãĥ©
    -0.16
    aln
    -0.16
    ãĥ³ãĤ°
    -0.15
     ÐĿаз
    -0.15
    inte
    -0.14
    asz
    -0.14
    \Component
    -0.14
    оÑī
    -0.14
    propri
    -0.14
    eff
    -0.14
    POSITIVE LOGITS
    wealth
    0.19
    rens
    0.15
    ith
    0.15
    Å¡t
    0.15
     Stem
    0.14
    aly
    0.14
    auer
    0.14
    stem
    0.14
    zym
    0.14
    /general
    0.14
    Act Density 0.121%

    No Known Activations