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

    Neuronpedia

    INDEX
    Explanations

    LaTeX or mathematical notation within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.64
    Còn
    -0.62
    IntoConstraints
    -0.62
    revenge
    -0.60
    adecimal
    -0.59
     незавершена
    -0.59
    ButterKnife
    -0.58
     Monfieur
    -0.57
     วาด
    -0.57
    opcional
    -0.57
    POSITIVE LOGITS
     $\
    1.40
    $\
    1.20
     $(
    0.91
     ${
    0.91
     $)$
    0.84
     ${\
    0.81
    ${
    0.77
    modelBuilder
    0.75
     $=
    0.75
     $
    0.74
    Act Density 0.552%

    No Known Activations