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

    Neuronpedia

    INDEX
    Explanations

    functions and terms related to the process of updating in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    san
    -0.65
    s
    -0.63
    Personendaten
    -0.63
     Cors
    -0.59
     Khur
    -0.58
    iverr
    -0.55
     Gim
    -0.55
    PMailer
    -0.55
    SneakyThrows
    -0.54
     Geh
    -0.54
    POSITIVE LOGITS
     Update
    1.93
     update
    1.92
    Update
    1.82
     UPDATE
    1.78
     Updates
    1.78
    update
    1.77
     updates
    1.76
     updater
    1.64
    updates
    1.64
     updating
    1.60
    Act Density 0.039%

    No Known Activations