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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that indicate a conclusion or final thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '{@
    -1.03
     ostavi
    -1.01
     BoxDecoration
    -0.95
    出版年
    -0.95
     ―――――
    -0.94
    ✨:
    -0.92
     snippetHide
    -0.90
    ſelves
    -0.90
    InputBorder
    -0.90
    ChildScrollView
    -0.90
    POSITIVE LOGITS
     and
    1.01
     This
    0.89
     The
    0.89
     It
    0.85
     There
    0.85
    ↵↵
    0.84
    The
    0.82
     Also
    0.82
     However
    0.81
    and
    0.79
    Act Density 0.298%

    No Known Activations