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

    Neuronpedia

    INDEX
    Explanations

    technical terms and jargon related to computing and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.75
     Majefty
    -0.69
     esternos
    -0.69
     يتيمه
    -0.68
    ſelves
    -0.64
     theoretically
    -0.63
     academically
    -0.63
    verwijspagina
    -0.61
     piele
    -0.61
     Safely
    -0.60
    POSITIVE LOGITS
    zy
    0.72
    cop
    0.69
     pu
    0.68
    lar
    0.67
     cop
    0.65
     Rub
    0.62
     rub
    0.61
    ima
    0.59
    LAR
    0.58
     oc
    0.58
    Act Density 1.853%

    No Known Activations