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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     theirs
    -0.60
     transfieras
    -0.59
     אתם
    -0.58
     masz
    -0.57
     hers
    -0.55
     ihr
    -0.54
     jij
    -0.53
    くださいね
    -0.53
     będ
    -0.52
     yake
    -0.52
    POSITIVE LOGITS
    脚注の使い方
    0.45
     mink
    0.43
    ங்கள
    0.38
     저
    0.37
     wet
    0.36
     nost
    0.36
     ModelExpression
    0.35
    bootstrapcdn
    0.35
     InputDecoration
    0.35
    ResourceBundle
    0.34
    Act Density 0.204%

    No Known Activations