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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significance or importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢава
    -0.15
    urch
    -0.15
    mond
    -0.15
     Sesso
    -0.14
    _Level
    -0.14
    eding
    -0.14
    ết
    -0.13
    ernals
    -0.13
     Kurum
    -0.13
    ep
    -0.13
    POSITIVE LOGITS
    ownik
    0.17
    ÑĮогоднÑĸ
    0.17
     part
    0.15
    olley
    0.14
    olik
    0.14
    kins
    0.13
     skill
    0.13
    arak
    0.13
    HashCode
    0.13
    role
    0.13
    Act Density 0.034%

    No Known Activations