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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and class definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeper
    -0.16
    ardi
    -0.15
    ÑĢоÑĪ
    -0.15
     twin
    -0.14
    .ContentType
    -0.14
     mini
    -0.14
    æĪĴ
    -0.14
     Bender
    -0.14
     nil
    -0.14
    ca
    -0.14
    POSITIVE LOGITS
    Ljava
    0.23
    rides
    0.18
    VOKE
    0.17
    etsk
    0.16
    )V
    0.15
    annon
    0.15
    etch
    0.15
    undaki
    0.14
    thes
    0.14
    ulp
    0.14
    Act Density 0.003%

    No Known Activations