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

    Neuronpedia

    INDEX
    Explanations

    categorical distinctions and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģn
    -0.16
    argout
    -0.16
    enser
    -0.14
    ritch
    -0.14
    OTAL
    -0.14
    Å¡Å¥
    -0.14
    }->{
    -0.14
    ánh
    -0.14
    ë³µ
    -0.13
    pread
    -0.13
    POSITIVE LOGITS
     ones
    0.15
     edm
    0.15
    ÙĪتÛĮ
    0.14
    ájem
    0.14
    vez
    0.14
    ãĥ³ãĥķ
    0.14
    masked
    0.13
    obili
    0.13
    andles
    0.13
     apt
    0.13
    Act Density 0.037%

    No Known Activations