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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pers
    -0.15
    ारà¤ķ
    -0.15
    irtual
    -0.14
    æ±Ĥ
    -0.14
    ClassLoader
    -0.14
     eh
    -0.13
     Robinson
    -0.13
     surfaces
    -0.13
     ydk
    -0.13
     Burger
    -0.13
    POSITIVE LOGITS
     response
    0.56
     Response
    0.52
    response
    0.48
    -response
    0.44
    Response
    0.44
    _response
    0.42
    .response
    0.41
     RESPONSE
    0.41
    (response
    0.41
     responded
    0.40
    Act Density 0.196%

    No Known Activations