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

    Neuronpedia

    INDEX
    Explanations

    references to programming constructs and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheon
    -0.19
    Schedulers
    -0.16
     Kraj
    -0.15
    ÙĦÛĮÙĦ
    -0.15
    rypton
    -0.15
    aleb
    -0.14
     Abrams
    -0.14
    REFERRED
    -0.14
    Ùĩر
    -0.14
    opsis
    -0.14
    POSITIVE LOGITS
     Luc
    0.28
     luc
    0.27
    Luc
    0.26
     boost
    0.23
    Sol
    0.22
    boost
    0.22
     Sol
    0.21
    _boost
    0.21
     boosting
    0.21
    .lucene
    0.21
    Act Density 0.026%

    No Known Activations