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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used to denote pauses or breaks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Penna
    -0.69
    Parcelize
    -0.68
     (_,
    -0.67
    listdir
    -0.67
    ,…
    -0.66
     AppBar
    -0.64
    ,...,
    -0.64
    AccessorTable
    -0.64
    żeń
    -0.63
     Lue
    -0.63
    POSITIVE LOGITS
     but
    0.77
     although
    0.73
     потому
    0.70
     thus
    0.69
     which
    0.67
     though
    0.65
     thereby
    0.64
    úrate
    0.63
     therefore
    0.63
     hence
    0.62
    Act Density 0.695%

    No Known Activations