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

    Neuronpedia

    INDEX
    Explanations

    terms related to theoretical concepts and ease of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.71
     siihen
    -0.64
     kautta
    -0.64
     nahilalakip
    -0.62
    antaranya
    -0.62
    delwed
    -0.61
     stället
    -0.61
     namanya
    -0.61
     Económica
    -0.61
     meille
    -0.60
    POSITIVE LOGITS
     Easy
    0.70
    Easy
    0.58
     theoretical
    0.57
     EASY
    0.55
    easy
    0.54
     Lan
    0.53
     Theoretical
    0.53
     easy
    0.53
     funeral
    0.52
     counselor
    0.52
    Act Density 0.201%

    No Known Activations