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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     far
    -0.55
     further
    -0.54
     conf
    -0.49
    πο
    -0.48
     we
    -0.48
     plus
    -0.47
     exp
    -0.46
     he
    -0.46
    '],$
    -0.46
    weit
    -0.46
    POSITIVE LOGITS
     nahilalakip
    1.16
    IntoConstraints
    0.97
     تضيفلها
    0.90
    Vidite
    0.90
     utafitiHapana
    0.88
     pinulongan
    0.82
    WriteTagHelper
    0.82
    UnusedPrivate
    0.81
    ImageContext
    0.79
    GEBURTSDATUM
    0.79
    Act Density 0.157%

    No Known Activations