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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "there" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.79
    insee
    -0.59
    PreferredItem
    -0.57
    DockStyle
    -0.56
    RenderAtEndOf
    -0.55
    hatian
    -0.54
    +#+
    -0.53
     EconPapers
    -0.53
    {(-
    -0.53
    earn
    -0.51
    POSITIVE LOGITS
     are
    1.05
     aren
    0.93
     were
    0.91
     weren
    0.85
     arent
    0.77
     ARE
    0.72
     WERE
    0.71
     isn
    0.69
     was
    0.69
     is
    0.69
    Act Density 0.166%

    No Known Activations