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

    Neuronpedia

    INDEX
    Explanations

    elements of mathematical expressions and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.21
     raiſ
    -1.20
     Efq
    -1.20
     ſtate
    -1.18
     ſche
    -1.18
     pleaſure
    -1.17
     ſever
    -1.16
     ſta
    -1.16
     uſ
    -1.13
     Reſ
    -1.12
    POSITIVE LOGITS
     
    0.86
     The
    0.76
    </h2>
    0.68
      
    0.66
    ↵↵
    0.66
     “
    0.65
     a
    0.65
     "
    0.62
     the
    0.60
     In
    0.58
    Act Density 3.594%

    No Known Activations