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

    Neuronpedia

    INDEX
    Explanations

    specific types of informal expressions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utz
    -0.16
    ardash
    -0.15
    Ä©
    -0.15
    ären
    -0.15
     (_,
    -0.14
    arra
    -0.14
    assium
    -0.14
    aggio
    -0.14
    ÑħÑĥ
    -0.14
    cae
    -0.13
    POSITIVE LOGITS
    udit
    0.15
    ê·¼
    0.15
     analogy
    0.14
    dal
    0.14
    oka
    0.14
    APS
    0.14
    igne
    0.14
    иÑĢа
    0.14
    dol
    0.14
    ÑĮ
    0.13
    Act Density 0.003%

    No Known Activations