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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a significant increase or surge in occurrences or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĤãģĨ
    -0.16
    .foundation
    -0.15
    akes
    -0.15
    ame
    -0.15
    ulo
    -0.14
    aldi
    -0.14
    HEET
    -0.14
    Updates
    -0.14
    /releases
    -0.14
     Changes
    -0.14
    POSITIVE LOGITS
     drop
    0.38
     rise
    0.35
     increase
    0.35
     jump
    0.34
     decrease
    0.32
     marked
    0.30
     spike
    0.28
     upt
    0.28
    increase
    0.27
     decline
    0.27
    Act Density 0.163%

    No Known Activations