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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases related to category listings and requests for proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beek
    -0.47
     aleación
    -0.43
    struktion
    -0.42
    jectures
    -0.41
     habido
    -0.41
    ningens
    -0.41
     hauts
    -0.40
     calzado
    -0.40
     élevés
    -0.40
     maneiras
    -0.40
    POSITIVE LOGITS
     ſeveral
    0.58
     whoſe
    0.57
     myſelf
    0.56
     becauſe
    0.55
     himſelf
    0.55
     Monfieur
    0.54
     themſelves
    0.53
    Ведь
    0.53
     ſhe
    0.52
     defaultstate
    0.52
    Act Density 0.048%

    No Known Activations