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

    Neuronpedia

    INDEX
    Explanations

    introductory sentences or phrases that signal the start of a new topic or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoresizingMask
    -0.85
    DockStyle
    -0.77
    lgari
    -0.68
    cipar
    -0.66
     apologised
    -0.66
    PMailer
    -0.66
     Theſe
    -0.65
     Senado
    -0.65
    хьтан
    -0.64
    epy
    -0.63
    POSITIVE LOGITS
    LOCAL
    0.53
     softball
    0.52
    ниципа
    0.52
    Local
    0.51
     Softball
    0.49
     underage
    0.47
     Local
    0.47
    demic
    0.47
     varsity
    0.46
     juniors
    0.46
    Act Density 0.156%

    No Known Activations