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

    Neuronpedia

    INDEX
    Explanations

    references to methodologies and techniques in scientific analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.46
     znamen
    -0.45
    inspira
    -0.43
     dedicar
    -0.43
     nécessairement
    -0.42
     naudo
    -0.41
     disesuaikan
    -0.41
     dedicada
    -0.41
     perspectiva
    -0.40
     paraître
    -0.40
    POSITIVE LOGITS
    character
    0.90
     character
    0.89
     characterize
    0.89
     Character
    0.82
    Character
    0.75
     infer
    0.74
     discriminate
    0.72
     reconstruct
    0.71
     estimate
    0.65
     reproduce
    0.65
    Act Density 1.510%

    No Known Activations