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

    Neuronpedia

    INDEX
    Explanations

    programming and software development-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antu
    -0.16
    onas
    -0.16
    581
    -0.15
    ernal
    -0.14
    lict
    -0.14
    []
    -0.14
    oga
    -0.14
    anych
    -0.14
    .gwt
    -0.14
    erap
    -0.13
    POSITIVE LOGITS
     scal
    0.25
     cats
    0.24
    cats
    0.23
     spray
    0.22
     shape
    0.20
     sco
    0.19
     scala
    0.19
    _cats
    0.18
    shape
    0.18
    scal
    0.18
    Act Density 0.003%

    No Known Activations