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

    Neuronpedia

    INDEX
    Explanations

    terms related to correctness and propriety in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     successfully
    -0.46
     successful
    -0.45
    success
    -0.42
     úspě
    -0.40
     başarı
    -0.40
     favorable
    -0.39
     better
    -0.38
     favorably
    -0.38
    successful
    -0.37
    successfully
    -0.36
    POSITIVE LOGITS
     timing
    0.85
     proportions
    0.79
     sized
    0.77
    StoreMessageInfo
    0.72
     Timing
    0.71
     placement
    0.70
     combination
    0.69
     sizing
    0.68
     noDo
    0.67
     alignment
    0.66
    Act Density 0.583%

    No Known Activations