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

    Neuronpedia

    INDEX
    Explanations

    conditional or situational phrases in contexts that may imply restrictions or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.90
    AccessorTable
    -0.76
    RegistryLite
    -0.75
     betweenstory
    -0.74
     تضيفلها
    -0.71
    oneph
    -0.69
    eeq
    -0.67
     pstmt
    -0.67
     Administrativna
    -0.66
    MessageOf
    -0.65
    POSITIVE LOGITS
    enough
    0.70
     enough
    0.70
     scolaires
    0.67
     malade
    0.60
     demais
    0.57
     envers
    0.57
     étrangères
    0.55
    RunWith
    0.54
     سازی
    0.53
     connaissent
    0.52
    Act Density 0.481%

    No Known Activations