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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate complex actions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.84
    nitř
    -0.80
     تضيفلها
    -0.72
    ficulty
    -0.71
    .}~\
    -0.67
    leyball
    -0.65
    FirebaseDatabase
    -0.64
    initely
    -0.63
    tingu
    -0.63
    IANGLES
    -0.62
    POSITIVE LOGITS
     /\.(
    0.56
    Rüyada
    0.53
    <bos>
    0.50
    Schedulers
    0.49
     tinggi
    0.49
    Становништво
    0.48
     متعلقه
    0.47
    />
    0.45
     Roskov
    0.44
     Courant
    0.44
    Act Density 0.668%

    No Known Activations