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

    Neuronpedia

    INDEX
    Explanations

    actions related to learning, teaching, and using various processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     /^(
    -0.16
    utto
    -0.15
    ington
    -0.15
    yne
    -0.14
    bew
    -0.14
    ovny
    -0.14
     inse
    -0.13
     plates
    -0.13
    owed
    -0.13
    qu
    -0.13
    POSITIVE LOGITS
     compared
    0.22
     even
    0.18
    even
    0.18
     yourself
    0.18
     oneself
    0.17
    Ñĥй
    0.15
    osp
    0.14
    ãĤīãģĽ
    0.14
    ÑĤаб
    0.14
    DD
    0.14
    Act Density 0.102%

    No Known Activations