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

    Neuronpedia

    INDEX
    Explanations

    references to primary entities or concepts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -0.71
     humanidade
    -0.70
    contentLoaded
    -0.68
     citoy
    -0.65
     للاسماء
    -0.64
     męska
    -0.64
     ſich
    -0.62
     unicórnio
    -0.61
     própri
    -0.61
    IsContent
    -0.60
    POSITIVE LOGITS
     confirmation
    0.66
    confirm
    0.63
     Confirm
    0.61
    Confirm
    0.58
     mention
    0.58
     confirm
    0.57
    confirmation
    0.57
     Confirmation
    0.57
     mentions
    0.56
    Confirmation
    0.55
    Act Density 0.315%

    No Known Activations