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

    Neuronpedia

    INDEX
    Explanations

    art-related language focusing on abstract concepts and creative expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Waſſer
    -0.75
     ſeinen
    -0.73
     dieſer
    -0.73
     ſind
    -0.71
     Anſ
    -0.71
     ſei
    -0.71
    addCriterion
    -0.70
     geſch
    -0.69
     müſſen
    -0.69
     purpoſe
    -0.69
    POSITIVE LOGITS
     particularly
    0.61
     vooral
    0.59
    particularly
    0.56
     principalement
    0.56
     especially
    0.54
     principalmente
    0.51
     primarily
    0.51
     surtout
    0.51
     especialmente
    0.51
     soprattutto
    0.50
    Act Density 0.593%

    No Known Activations