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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contradiction or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entweder
    -0.52
    newArrayList
    -0.49
    .
    -0.48
     sekaligus
    -0.47
    eltjes
    -0.46
    extAlignment
    -0.46
     porque
    -0.46
    porque
    -0.46
    WriteAttribute
    -0.45
    ".
    -0.44
    POSITIVE LOGITS
     this
    0.88
     all
    0.87
     recent
    0.85
     everything
    0.84
     propOrder
    0.81
     these
    0.80
     today
    0.77
     hindsight
    0.77
     مشين
    0.75
     such
    0.75
    Act Density 0.380%

    No Known Activations