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

    Neuronpedia

    INDEX
    Explanations

    words with diacritical marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.82
    almaz
    -0.55
    ViewFeatures
    -0.50
    núť
    -0.49
    kosti
    -0.48
    bigsqcup
    -0.47
     Mont
    -0.47
    umlu
    -0.47
    wiec
    -0.47
     برابوك
    -0.47
    POSITIVE LOGITS
    loé
    0.78
     defaultstate
    0.77
     تضيفلها
    0.77
     Erdoğan
    0.76
     consultato
    0.73
     itſelf
    0.71
    Atlético
    0.70
    interopRequire
    0.70
    InputModule
    0.69
    tréal
    0.69
    Act Density 0.934%

    No Known Activations