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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing degrees or measures of quantity and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viation
    -0.47
    ấu
    -0.46
    bihan
    -0.46
     sponsored
    -0.45
    ⎪
    -0.45
    tation
    -0.45
    trie
    -0.45
    tiek
    -0.44
    addItem
    -0.44
    andescent
    -0.44
    POSITIVE LOGITS
     to
    1.54
    to
    1.21
     TO
    1.19
    To
    1.11
     To
    1.09
     לה
    1.05
     להת
    0.93
     να
    0.90
     לס
    0.89
    TO
    0.89
    Act Density 0.174%

    No Known Activations