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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections or significant breaks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.11
    endphp
    -1.09
     houſe
    -1.06
    GraphicsUnit
    -1.05
     iſt
    -1.03
     pleaſure
    -1.02
    ChildScrollView
    -1.02
     raiſ
    -1.01
     purpoſe
    -0.99
    RenderAtEndOf
    -0.98
    POSITIVE LOGITS
     
    0.78
    <bos>
    0.72
     B
    0.62
     a
    0.54
     i
    0.54
    3
    0.54
     D
    0.53
    2
    0.53
     $\
    0.52
     e
    0.52
    Act Density 0.613%

    No Known Activations