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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or building upon previous achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    building on or upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RequestMethod
    -0.55
     Administrativna
    -0.47
    .*")]
    -0.43
    =$?
    -0.43
    WillAppear
    -0.42
    __;
    -0.42
     moderators
    -0.39
     getRule
    -0.39
    ContentAsync
    -0.39
     DbType
    -0.39
    POSITIVE LOGITS
     tradizione
    0.57
    Beyond
    0.56
    existing
    0.55
     tradición
    0.55
     enhancing
    0.54
    Already
    0.54
    Tikang
    0.54
    Building
    0.54
    enhance
    0.53
    grunn
    0.53
    Act Density 0.010%

    No Known Activations