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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases that seek clarification or identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SafeMath
    -0.70
    uxley
    -0.62
     = 
    -0.61
    ])).
    -0.60
     Familienname
    -0.59
    toolbox
    -0.58
    remoto
    -0.56
    ngdoc
    -0.55
     Foxx
    -0.55
    loroethane
    -0.55
    POSITIVE LOGITS
     distinguish
    0.80
     distinguishing
    0.78
     discerned
    0.76
     Unterscheidung
    0.74
     distinguir
    0.72
     discern
    0.72
     distinguer
    0.72
     tell
    0.70
     discer
    0.70
    distingu
    0.70
    Act Density 0.471%

    No Known Activations