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

    Neuronpedia

    INDEX
    Explanations

    programming keywords and logical constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ²¢
    -0.16
    atz
    -0.15
    829
    -0.15
    oling
    -0.15
    zan
    -0.15
    ivan
    -0.14
    ----------</
    -0.14
    ozor
    -0.14
    _RSA
    -0.13
    RIX
    -0.13
    POSITIVE LOGITS
     _
    0.65
    _
    0.27
    ._
    0.25
    -_
    0.24
    ãĢĬ
    0.23
    Âł
    0.22
     **
    0.22
    0.21
     ãĢĬ
    0.21
    (_
    0.21
    Act Density 0.009%

    No Known Activations