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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Ti" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.16
    oven
    -0.15
    umm
    -0.15
    ãĥ¥ãĥ¼
    -0.15
    ington
    -0.15
    umn
    -0.14
    ÑħÑĸв
    -0.14
    umi
    -0.14
    aver
    -0.14
    conte
    -0.14
    POSITIVE LOGITS
    erra
    0.22
    Vo
    0.20
    ếp
    0.20
    empo
    0.19
    ivist
    0.19
    .include
    0.18
    roid
    0.17
    ARA
    0.17
    endas
    0.17
    erno
    0.17
    Act Density 0.012%

    No Known Activations