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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating relationships, distinctions, and organization within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNUSED
    -0.16
    iyon
    -0.16
    ););↵
    -0.15
    irt
    -0.14
    à¹ĭ
    -0.13
    rr
    -0.13
    au
    -0.13
    िà¤Ĺ
    -0.13
    .addTarget
    -0.13
    .maven
    -0.13
    POSITIVE LOGITS
    :↵
    0.42
    :↵↵
    0.38
     :↵
    0.35
    :č↵
    0.33
    ):↵
    0.32
    ï¼ļ↵
    0.31
     :↵↵
    0.31
    ():↵
    0.30
    ":↵
    0.30
    ]:↵
    0.30
    Act Density 0.188%

    No Known Activations