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

    Neuronpedia

    INDEX
    Explanations

    instances of conversational transitions and the use of dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quet
    -0.15
    awl
    -0.15
    468
    -0.15
    _refl
    -0.14
    ledo
    -0.14
    ãĥ¼ãĥ«
    -0.14
    atcher
    -0.14
    ertas
    -0.14
    .flash
    -0.14
    jev
    -0.14
    POSITIVE LOGITS
    ureau
    0.17
    lava
    0.16
    (before
    0.16
    ¤¤
    0.15
    obili
    0.14
     Benton
    0.14
    yms
    0.14
    Ģ
    0.14
    ä»ĺ
    0.14
    stanov
    0.14
    Act Density 0.048%

    No Known Activations