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

    Neuronpedia

    INDEX
    Explanations

    instances of time notations, particularly "AM" and "PM."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    AM or PM timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bolsillos
    -0.61
     excelencia
    -0.60
     herido
    -0.57
     vendido
    -0.57
     obligado
    -0.56
     aislado
    -0.56
     femeninos
    -0.56
     ladrillo
    -0.54
     sostenibilidad
    -0.54
     doméstico
    -0.54
    POSITIVE LOGITS
     PM
    1.61
    PM
    1.20
     AM
    0.83
    PMD
    0.69
     下午
    0.67
     VM
    0.66
     RM
    0.65
     MM
    0.64
     CM
    0.64
     DM
    0.62
    Act Density 0.004%

    No Known Activations