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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and expressions of passion or dedication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Trouble
    -0.55
    hdys
    -0.54
     complained
    -0.52
     quæ
    -0.51
    但也
    -0.50
    ługi
    -0.48
    king
    -0.47
    mostly
    -0.47
     sejumlah
    -0.46
     preferred
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.74
     snippetHide
    0.73
    脚注の使い方
    0.70
     passion
    0.69
     partage
    0.66
     spirit
    0.65
     propOrder
    0.65
     AssemblyVersion
    0.64
     creativity
    0.64
     passionate
    0.63
    Act Density 0.265%

    No Known Activations