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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating secrecy or anonymity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sanitaires
    -0.48
     lätt
    -0.47
    ору
    -0.45
     extérieures
    -0.42
     EdgeInsets
    -0.42
     rings
    -0.41
    entina
    -0.41
     uova
    -0.40
     occurrence
    -0.40
    uelle
    -0.40
    POSITIVE LOGITS
    Personendaten
    1.01
    aarrggbb
    0.86
    verwijspagina
    0.80
     reportedly
    0.77
     intptr
    0.77
     disambiguazione
    0.72
     kaarangay
    0.70
    èdia
    0.70
     createSlice
    0.70
    ंदीखरीदारी
    0.69
    Act Density 0.235%

    No Known Activations