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

    Neuronpedia

    INDEX
    Explanations

    terms related to mild or moderate qualities and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @qq
    -0.19
    ean
    -0.19
    ãģĤãģĴ
    -0.18
    nit
    -0.15
    orting
    -0.15
    574
    -0.14
    roperties
    -0.14
    cheng
    -0.14
    fully
    -0.14
    را
    -0.14
    POSITIVE LOGITS
    ewed
    0.28
    /mod
    0.24
    ly
    0.23
     (<
    0.22
    ew
    0.21
    ãģªãģĮãĤī
    0.21
    /small
    0.21
    -medium
    0.20
    ewing
    0.19
    urn
    0.19
    Act Density 0.082%

    No Known Activations